Terminal-Bench 4.0
The official leaderboard hasn’t scored a model released after GPT-6.1 Terra (October 2026). Labs report their own numbers for 9 newer models, such as Claude Fable 5.2 at 67.6%.
Agents complete 66 hard tasks in containerized terminals across software, ML, science, security, and operations. Test scripts verify each result, scored as resolution rate.
It removed 8 saturated or flawed tasks from Terminal-Bench 3.0 and set a flat 8-hour agent timeout.
- Made by
- Stanford University, Harbor, and Laude Institute
- Released
- August 2026
- Kind
- Terminal tasks
- Level
- Expert
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Agentic
- Environment
- Terminal
- Items from
- Another benchmark
- Refresh
- New versions replace it
- Run by
- Anyone
- Based on
- Terminal-Bench 3.0
- In views
- Agents
- Strongest model tested
- Claude Fable 5.2 #2 on the capability index
- Last in a launch post
- November 2026
- Last model added
- November 2026
- Scores refreshed
- November 20th, 2026
Claude Opus 5.5 leads with 64.8% Claude Opus 5.5 leads with 64.8% MiMo-V2.6 Pro leads with 27% in mini-SWE-agent
Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran on its own with several settings, we keep its best. Every run is in the next chart. Agents other companies built around a model get a pale shade of that model's lab color. Gray marks blends and entries not in our model list, such as fine-tunes and older models. None of these count toward leaders. Agents built around a model, such as Claude Code + Kimi K3.1 Pro, are their own entries. We don't count them as the model's score. This view shows only models we track, each at its best. This view keeps only runs in mini-SWE-agent, a harness no model’s maker built. A maker’s own agent, such as Claude Code with a Claude model, is left out.
Claude Sonnet 5.5 leads with 70.6%, claims included
Best score per model from every source, including labs’ own numbers and claims Epoch AI collected from reports and papers. Labs pick their own settings, so a claim can beat an independent run of the same model. Striped bars are claims, and dotted bars are reruns by Epoch AI or another board.
- 64.8 Claude Opus 5.5
- 61.8 Claude Sonnet 5.5
- 60.9 Claude Code + Kimi K3.1 Pro
- 58.2 GPT-6 Astra
- 58.2 GPT-6.1 Sol
- 57.9 Claude Fable 5.1
- 54.9
Gemini 4 Argon
- 53.9 Claude Opus 5
- 51.8 GPT-6.1 Terra
- 49.4 GPT-6 Sol
- 47.0
Muse Wonder
- 44.5 Claude Fable 5
- 41.8 Claude Code + GLM-5.3
- 40.0 Claude Haiku 5.5
- 40.0 Claude Code + DeepSeek V4.1 Flash 1017
- 39.1 Claude Code + Tencent Hy4
- 37.6 Grok 4.7
- 37.3 GPT-5.6 Sol
- 36.7 Claude Code + GLM-5.3-Flash
- 27.9 Claude Code + Mistral Large 4
- 27.0 Claude Code + Qwen3.8 Max (0902)
- 27.0 MiMo-V2.6 Pro
- 23.6 Claude Opus 4.8
- 22.4 Claude Code + Kimi K3
- 21.8
Ember-1
- 21.5 GPT-5.6 Terra
- 20.3 Grok 4.6
- 19.4 Claude Code + Tencent Hy4 preview
- 19.1
Gemini 3.8 Flash
- 17.3 GPT-5.6 Luna
- 16.4 GPT-6 Luna
- 16.1 MiMo-V2.6 Flash
- 14.6
Muse Spark 1.3
- 12.4 Claude Sonnet 5
- 12.4 Grok 4.5
- 11.2
Gemini 3.7 Flash
- 7.27
MiniMax-M3
- 6.67 Claude Code + DeepSeek V4 Pro 0813
- 6.36 Beam 1.0
- 2.73
Gemini 3.1 Pro
- 1.82 GPT-5.4 Mini
- 0.91
Inkling-Small
- 0.30
Nemotron 3.5 Super VL
- 0.0
Inkling
- 1 Claude Opus 5.5 max 64.8%
- 2 Claude Sonnet 5.5 max 61.8%
- 3 Claude Code + Kimi K3.1 Pro max 60.9%
- 4 GPT-6 Astra max 58.2%
- 5 GPT-6.1 Sol max 58.2%
- 6 Claude Fable 5.1 max 57.9%
- 7
Gemini 4 Argon high 54.9%
- 8 Claude Opus 5 xhigh 53.9%
- 9 GPT-6.1 Terra max 51.8%
- 10 GPT-6 Sol max 49.4%
- 11
Muse Wonder xhigh 47%
- 12 Claude Fable 5 max 44.5%
- 13 Claude Code + GLM-5.3 max 41.8%
- 14 Claude Haiku 5.5 max 40%
- 15 Claude Code + DeepSeek V4.1 Flash 1017 max 40%
- 16 Claude Code + Tencent Hy4 max 39.1%
- 17 Grok 4.7 xhigh 37.6%
- 18 GPT-5.6 Sol max 37.3%
- 19 Claude Code + GLM-5.3-Flash max 36.7%
- 20 Claude Code + Mistral Large 4 max 27.9%
- 21 Claude Code + Qwen3.8 Max (0902) max 27%
- 22 MiMo-V2.6 Pro none 27%
- 23 Claude Opus 4.8 max 23.6%
- 24 Claude Code + Kimi K3 max 22.4%
- 25
Ember-1 none 21.8%
- 26 GPT-5.6 Terra max 21.5%
- 27 Grok 4.6 high 20.3%
- 28 Claude Code + Tencent Hy4 preview max 19.4%
- 29
Gemini 3.8 Flash high 19.1%
- 30 GPT-5.6 Luna max 17.3%
- 31 GPT-6 Luna max 16.4%
- 32 MiMo-V2.6 Flash none 16.1%
- 33
Muse Spark 1.3 xhigh 14.6%
- 34 Claude Sonnet 5 max 12.4%
- 35 Grok 4.5 high 12.4%
- 36
Gemini 3.7 Flash high 11.2%
- 37
MiniMax-M3 none 7.27%
- 38 Claude Code + DeepSeek V4 Pro 0813 max 6.67%
- 39 Beam 1.0 none 6.36%
- 40
Gemini 3.1 Pro high 2.73%
- 41 GPT-5.4 Mini xhigh 1.82%
- 42
Inkling-Small none 0.91%
- 43
Nemotron 3.5 Super VL none 0.30%
- 44
Inkling none 0%
Source: Official Terminal-Bench 4.0 leaderboard
- 64.8 Claude Opus 5.5
- 61.8 Claude Sonnet 5.5
- 58.2 GPT-6 Astra
- 58.2 GPT-6.1 Sol
- 57.9 Claude Fable 5.1
- 54.9
Gemini 4 Argon
- 53.9 Claude Opus 5
- 51.8 GPT-6.1 Terra
- 49.4 GPT-6 Sol
- 47.0
Muse Wonder
- 44.5 Claude Fable 5
- 40.0 Claude Haiku 5.5
- 37.6 Grok 4.7
- 37.3 GPT-5.6 Sol
- 27.0 MiMo-V2.6 Pro
- 23.6 Claude Opus 4.8
- 21.8
Ember-1
- 21.5 GPT-5.6 Terra
- 20.3 Grok 4.6
- 19.1
Gemini 3.8 Flash
- 17.3 GPT-5.6 Luna
- 16.4 GPT-6 Luna
- 16.1 MiMo-V2.6 Flash
- 14.6
Muse Spark 1.3
- 12.4 Claude Sonnet 5
- 12.4 Grok 4.5
- 11.2
Gemini 3.7 Flash
- 7.27
MiniMax-M3
- 6.36 Beam 1.0
- 2.73
Gemini 3.1 Pro
- 1.82 GPT-5.4 Mini
- 0.91
Inkling-Small
- 0.30
Nemotron 3.5 Super VL
- 0.0
Inkling
- 1 Claude Opus 5.5 max 64.8%
- 2 Claude Sonnet 5.5 max 61.8%
- 3 GPT-6 Astra max 58.2%
- 4 GPT-6.1 Sol max 58.2%
- 5 Claude Fable 5.1 max 57.9%
- 6
Gemini 4 Argon high 54.9%
- 7 Claude Opus 5 xhigh 53.9%
- 8 GPT-6.1 Terra max 51.8%
- 9 GPT-6 Sol max 49.4%
- 10
Muse Wonder xhigh 47%
- 11 Claude Fable 5 max 44.5%
- 12 Claude Haiku 5.5 max 40%
- 13 Grok 4.7 xhigh 37.6%
- 14 GPT-5.6 Sol max 37.3%
- 15 MiMo-V2.6 Pro none 27%
- 16 Claude Opus 4.8 max 23.6%
- 17
Ember-1 none 21.8%
- 18 GPT-5.6 Terra max 21.5%
- 19 Grok 4.6 high 20.3%
- 20
Gemini 3.8 Flash high 19.1%
- 21 GPT-5.6 Luna max 17.3%
- 22 GPT-6 Luna max 16.4%
- 23 MiMo-V2.6 Flash none 16.1%
- 24
Muse Spark 1.3 xhigh 14.6%
- 25 Claude Sonnet 5 max 12.4%
- 26 Grok 4.5 high 12.4%
- 27
Gemini 3.7 Flash high 11.2%
- 28
MiniMax-M3 none 7.27%
- 29 Beam 1.0 none 6.36%
- 30
Gemini 3.1 Pro high 2.73%
- 31 GPT-5.4 Mini xhigh 1.82%
- 32
Inkling-Small none 0.91%
- 33
Nemotron 3.5 Super VL none 0.30%
- 34
Inkling none 0%
Source: Official Terminal-Bench 4.0 leaderboard
- 1 MiMo-V2.6 Pro none 27%
- 2
Ember-1 none 21.8%
- 3
Gemini 3.8 Flash high 19.1%
- 4 MiMo-V2.6 Flash none 16.1%
- 5
Gemini 3.7 Flash high 11.2%
- 6
MiniMax-M3 none 7.27%
- 7 Beam 1.0 none 6.36%
- 8
Inkling-Small none 0.91%
- 9
Nemotron 3.5 Super VL none 0.30%
- 10
Inkling none 0%
Source: Official Terminal-Bench 4.0 leaderboard
- 70.6 Claude Sonnet 5.5
- 67.6 Claude Fable 5.2
- 66.4 Claude Opus 5.5
- 65.7 Kimi K3.1 Pro
- 65.2
Gemini 4 Carbon
- 58.2 GPT-6 Astra
- 58.2 GPT-6.1 Sol
- 57.9 Claude Fable 5.1
- 57.4
Gemini 4 Argon
- 57.1
Muse Wonder Full
- 53.9 Claude Opus 5
- 52.0
Muse Wonder
- 51.8 GPT-6.1 Terra
- 49.4 GPT-6 Sol
- 48.5
Qwen4-Max
- 46.0
Ling-3.1-flash
- 44.5 Claude Fable 5
- 44.4
Tencent Hy4
- 42.3
DeepSeek V4.1 Flash 1017
- 41.0
Mistral Large 4 (Le Chonk, open weights)
- 40.9
Muse Ember
- 40.0 Claude Haiku 5.5
- 38.5
LongCat-2.5
- 38.1
MiniMax-M3.1-Flash
- 38.0 Grok 4.7
- 37.3 GPT-5.6 Sol
- 34.9 MiMo-V2.6 Pro
- 33.3
Step 5 Preview
- 31.2
DeepSeek V4.1 Flash
- 28.8 MiMo-V2.6 Flash
- 28.3
Mistral Large 4
- 27.3 SWE-2
- 23.6 Claude Opus 4.8
- 21.8
Ember-1
- 21.5 GPT-5.6 Terra
- 20.3 Grok 4.6
- 20.0 SWE-2 Flash
- 19.1
Gemini 3.8 Flash
- 17.3 GPT-5.6 Luna
- 16.4 GPT-6 Luna
- 14.6
Muse Spark 1.3
- 12.4 Claude Sonnet 5
- 12.4 Grok 4.5
- 11.2
Gemini 3.7 Flash
- 7.27
MiniMax-M3
- 6.36 Beam 1.0
- 5.60
Inkling 2 Mini
- 2.73
Gemini 3.1 Pro
- 1.82 GPT-5.4 Mini
- 1.00
Nemotron 3.5 Super VL
- 0.91
Inkling-Small
- 0.0
Inkling
- 1 Claude Sonnet 5.5 70.6%
- 2 Claude Fable 5.2 max effort 67.6%
- 3 Claude Opus 5.5 xhigh effort 66.4%
- 4 Kimi K3.1 Pro 65.7%
- 5
Gemini 4 Carbon 65.2%
- 6 GPT-6 Astra max 58.2%
- 7 GPT-6.1 Sol max 58.2%
- 8 Claude Fable 5.1 max 57.9%
- 9
Gemini 4 Argon 57.4%
- 10
Muse Wonder Full 57.1%
- 11 Claude Opus 5 xhigh 53.9%
- 12
Muse Wonder 52%
- 13 GPT-6.1 Terra max 51.8%
- 14 GPT-6 Sol max 49.4%
- 15
Qwen4-Max xhigh effort 48.5%
- 16
Ling-3.1-flash 46%
- 17 Claude Fable 5 max 44.5%
- 18
Tencent Hy4 44.4%
- 19
DeepSeek V4.1 Flash 1017 42.3%
- 20
Mistral Large 4 (Le Chonk, open weights) 41%
- 21
Muse Ember max effort 40.9%
- 22 Claude Haiku 5.5 max 40%
- 23
LongCat-2.5 38.5%
- 24
MiniMax-M3.1-Flash 38.1%
- 25 Grok 4.7 38%
- 26 GPT-5.6 Sol max 37.3%
- 27 MiMo-V2.6 Pro 34.9%
- 28
Step 5 Preview 33.3%
- 29
DeepSeek V4.1 Flash 31.2%
- 30 MiMo-V2.6 Flash 28.8%
- 31
Mistral Large 4 28.3%
- 32 SWE-2 27.3%
- 33 Claude Opus 4.8 max 23.6%
- 34
Ember-1 none 21.8%
- 35 GPT-5.6 Terra max 21.5%
- 36 Grok 4.6 high 20.3%
- 37 SWE-2 Flash 20%
- 38
Gemini 3.8 Flash 19.1%
- 39 GPT-5.6 Luna max 17.3%
- 40 GPT-6 Luna max 16.4%
- 41
Muse Spark 1.3 xhigh 14.6%
- 42 Claude Sonnet 5 max 12.4%
- 43 Grok 4.5 high 12.4%
- 44
Gemini 3.7 Flash high 11.2%
- 45
MiniMax-M3 none 7.27%
- 46 Beam 1.0 none 6.36%
- 47
Inkling 2 Mini 5.60%
- 48
Gemini 3.1 Pro high 2.73%
- 49 GPT-5.4 Mini xhigh 1.82%
- 50
Nemotron 3.5 Super VL 1.00%
- 51
Inkling-Small none 0.91%
- 52
Inkling none 0%
Sources: Labs’ model cards and official Terminal-Bench 4.0 leaderboard
| # | Entry | Score ± 95% CI | Setting | Agent by | Released | Run on | Source |
|---|---|---|---|---|---|---|---|
| 1 | Claude Opus 5.5 | 64.8% ±3.1 | max, Claude Code | Anthropic | Sep 2026 | Sep 2026 | Official leaderboard |
| 2 | Claude Sonnet 5.5 | 61.8% ±2.9 | max, Claude Code | Anthropic | Sep 2026 | Sep 2026 | Official leaderboard |
| 3 | Claude Code + Kimi K3.1 Pro | 60.9% ±4.1 | max | Anthropic | Oct 2026 | Oct 2026 | Official leaderboard |
| 4 | GPT-6 Astra | 58.2% ±2.8 | max, Codex | OpenAI | Sep 2026 | Sep 2026 | Official leaderboard |
| 5 | GPT-6.1 Sol | 58.2% ±3.1 | max, Codex | OpenAI | Sep 2026 | Sep 2026 | Official leaderboard |
| 6 | Claude Fable 5.1 | 57.9% ±3.8 | max, Claude Code | Anthropic | Sep 2026 | Sep 2026 | Official leaderboard |
| 7 | | 54.9% ±3 | high, Antigravity CLI | Sep 2026 | Sep 2026 | Official leaderboard | |
| 8 | Claude Opus 5 | 53.9% ±3.2 | xhigh, Claude Code | Anthropic | Jul 2026 | Jul 2026 | Official leaderboard |
| 9 | GPT-6.1 Terra | 51.8% ±2.8 | max, Codex | OpenAI | Oct 2026 | Oct 2026 | Official leaderboard |
| 10 | GPT-6 Sol | 49.4% ±3.2 | max, Codex | OpenAI | Sep 2026 | Sep 2026 | Official leaderboard |
| 11 | | 47% ±3.8 | xhigh, Muse Code | Meta | Oct 2026 | Oct 2026 | Official leaderboard |
| 12 | Claude Fable 5 | 44.5% ±3.8 | max, Claude Code | Anthropic | Jun 2026 | Jun 2026 | Official leaderboard |
| 13 | Claude Code + GLM-5.3 | 41.8% ±3.2 | max | Anthropic | Aug 2026 | Aug 2026 | Official leaderboard |
| 14 | Claude Haiku 5.5 | 40% ±3.7 | max, Claude Code | Anthropic | Oct 2026 | Oct 2026 | Official leaderboard |
| 15 | Claude Code + DeepSeek V4.1 Flash 1017 | 40% ±3.7 | max | Anthropic | Oct 2026 | Oct 2026 | Official leaderboard |
| 16 | Claude Code + Tencent Hy4 | 39.1% ±3.5 | max | Anthropic | Nov 2026 | Nov 2026 | Official leaderboard |
| 17 | Grok 4.7 | 37.6% ±3.5 | xhigh, Grok Build | xAI | Sep 2026 | Sep 2026 | Official leaderboard |
| 18 | GPT-5.6 Sol | 37.3% ±3.8 | max, Codex | OpenAI | Jul 2026 | Jun 2026 | Official leaderboard |
| 19 | Claude Code + GLM-5.3-Flash | 36.7% ±3.7 | max | Anthropic | Aug 2026 | Aug 2026 | Official leaderboard |
| 20 | Claude Code + Mistral Large 4 | 27.9% ±3.9 | max | Anthropic | Oct 2026 | Oct 2026 | Official leaderboard |
| 21 | Claude Code + Qwen3.8 Max (0902) | 27% ±3.8 | max | Anthropic | Sep 2026 | Sep 2026 | Official leaderboard |
| 22 | MiMo-V2.6 Pro | 27% ±3.6 | none, mini-swe-agent | SWE-agent | Sep 2026 | Sep 2026 | Official leaderboard |
| 23 | Claude Opus 4.8 | 23.6% ±3.6 | max, Claude Code | Anthropic | May 2026 | May 2026 | Official leaderboard |
| 24 | Claude Code + Kimi K3 | 22.4% ±3.8 | max | Anthropic | Jul 2026 | Jul 2026 | Official leaderboard |
| 25 | | 21.8% ±3.4 | none, mini-swe-agent | SWE-agent | Sep 2026 | Sep 2026 | Official leaderboard |
| 26 | GPT-5.6 Terra | 21.5% ±3.3 | max, Codex | OpenAI | Jul 2026 | Jun 2026 | Official leaderboard |
| 27 | Grok 4.6 | 20.3% ±3.1 | high, Grok Build | xAI | Aug 2026 | Aug 2026 | Official leaderboard |
| 28 | Claude Code + Tencent Hy4 preview | 19.4% ±3.1 | max | Anthropic | Aug 2026 | Aug 2026 | Official leaderboard |
| 29 | | 19.1% ±3.4 | high, mini-SWE-agent | SWE-agent | Sep 2026 | Sep 2026 | Official leaderboard |
| 30 | GPT-5.6 Luna | 17.3% ±2.9 | max, Codex | OpenAI | Jul 2026 | Jun 2026 | Official leaderboard |
| 31 | GPT-6 Luna | 16.4% ±2.7 | max, Codex | OpenAI | Sep 2026 | Sep 2026 | Official leaderboard |
| 32 | MiMo-V2.6 Flash | 16.1% ±3.4 | none, mini-swe-agent | SWE-agent | Sep 2026 | Sep 2026 | Official leaderboard |
| 33 | | 14.6% ±2.9 | xhigh, Muse Code | Meta | Sep 2026 | Sep 2026 | Official leaderboard |
| 34 | Claude Sonnet 5 | 12.4% ±3.1 | max, Claude Code | Anthropic | Jun 2026 | Jun 2026 | Official leaderboard |
| 35 | Grok 4.5 | 12.4% ±2.6 | high, Grok Build | xAI | Jul 2026 | Jul 2026 | Official leaderboard |
| 36 | | 11.2% ±2.5 | high, mini-SWE-agent | SWE-agent | Aug 2026 | Aug 2026 | Official leaderboard |
| 37 | | 7.27% ±2.7 | none, mini-swe-agent | SWE-agent | Jun 2026 | Jun 2026 | Official leaderboard |
| 38 | Claude Code + DeepSeek V4 Pro 0813 | 6.67% ±2.5 | max | Anthropic | Aug 2026 | Aug 2026 | Official leaderboard |
| 39 | Beam 1.0 | 6.36% ±1.7 | none, mini-swe-agent | SWE-agent | Oct 2026 | Oct 2026 | Official leaderboard |
| 40 | | 2.73% ±1.7 | high, Antigravity CLI | Feb 2026 | Feb 2026 | Official leaderboard | |
| 41 | GPT-5.4 Mini | 1.82% ±1.3 | xhigh, Codex | OpenAI | Mar 2026 | Mar 2026 | Official leaderboard |
| 42 | | 0.91% ±0.9 | none, mini-swe-agent | SWE-agent | Jul 2026 | Jul 2026 | Official leaderboard |
| 43 | | 0.30% ±0.6 | none, mini-swe-agent | SWE-agent | Oct 2026 | Oct 2026 | Official leaderboard |
| 44 | | 0% | none, mini-swe-agent | SWE-agent | Jul 2026 | Jul 2026 | Official leaderboard |
| # | Model | Score ± 95% CI | Setting | Agent by | Released | Run on | Source |
|---|---|---|---|---|---|---|---|
| 1 | Claude Opus 5.5 | 64.8% ±3.1 | max, Claude Code | Anthropic | Sep 2026 | Sep 2026 | Official leaderboard |
| 2 | Claude Sonnet 5.5 | 61.8% ±2.9 | max, Claude Code | Anthropic | Sep 2026 | Sep 2026 | Official leaderboard |
| 3 | GPT-6 Astra | 58.2% ±2.8 | max, Codex | OpenAI | Sep 2026 | Sep 2026 | Official leaderboard |
| 4 | GPT-6.1 Sol | 58.2% ±3.1 | max, Codex | OpenAI | Sep 2026 | Sep 2026 | Official leaderboard |
| 5 | Claude Fable 5.1 | 57.9% ±3.8 | max, Claude Code | Anthropic | Sep 2026 | Sep 2026 | Official leaderboard |
| 6 | | 54.9% ±3 | high, Antigravity CLI | Sep 2026 | Sep 2026 | Official leaderboard | |
| 7 | Claude Opus 5 | 53.9% ±3.2 | xhigh, Claude Code | Anthropic | Jul 2026 | Jul 2026 | Official leaderboard |
| 8 | GPT-6.1 Terra | 51.8% ±2.8 | max, Codex | OpenAI | Oct 2026 | Oct 2026 | Official leaderboard |
| 9 | GPT-6 Sol | 49.4% ±3.2 | max, Codex | OpenAI | Sep 2026 | Sep 2026 | Official leaderboard |
| 10 | | 47% ±3.8 | xhigh, Muse Code | Meta | Oct 2026 | Oct 2026 | Official leaderboard |
| 11 | Claude Fable 5 | 44.5% ±3.8 | max, Claude Code | Anthropic | Jun 2026 | Jun 2026 | Official leaderboard |
| 12 | Claude Haiku 5.5 | 40% ±3.7 | max, Claude Code | Anthropic | Oct 2026 | Oct 2026 | Official leaderboard |
| 13 | Grok 4.7 | 37.6% ±3.5 | xhigh, Grok Build | xAI | Sep 2026 | Sep 2026 | Official leaderboard |
| 14 | GPT-5.6 Sol | 37.3% ±3.8 | max, Codex | OpenAI | Jul 2026 | Jun 2026 | Official leaderboard |
| 15 | MiMo-V2.6 Pro | 27% ±3.6 | none, mini-swe-agent | SWE-agent | Sep 2026 | Sep 2026 | Official leaderboard |
| 16 | Claude Opus 4.8 | 23.6% ±3.6 | max, Claude Code | Anthropic | May 2026 | May 2026 | Official leaderboard |
| 17 | | 21.8% ±3.4 | none, mini-swe-agent | SWE-agent | Sep 2026 | Sep 2026 | Official leaderboard |
| 18 | GPT-5.6 Terra | 21.5% ±3.3 | max, Codex | OpenAI | Jul 2026 | Jun 2026 | Official leaderboard |
| 19 | Grok 4.6 | 20.3% ±3.1 | high, Grok Build | xAI | Aug 2026 | Aug 2026 | Official leaderboard |
| 20 | | 19.1% ±3.4 | high, mini-SWE-agent | SWE-agent | Sep 2026 | Sep 2026 | Official leaderboard |
| 21 | GPT-5.6 Luna | 17.3% ±2.9 | max, Codex | OpenAI | Jul 2026 | Jun 2026 | Official leaderboard |
| 22 | GPT-6 Luna | 16.4% ±2.7 | max, Codex | OpenAI | Sep 2026 | Sep 2026 | Official leaderboard |
| 23 | MiMo-V2.6 Flash | 16.1% ±3.4 | none, mini-swe-agent | SWE-agent | Sep 2026 | Sep 2026 | Official leaderboard |
| 24 | | 14.6% ±2.9 | xhigh, Muse Code | Meta | Sep 2026 | Sep 2026 | Official leaderboard |
| 25 | Claude Sonnet 5 | 12.4% ±3.1 | max, Claude Code | Anthropic | Jun 2026 | Jun 2026 | Official leaderboard |
| 26 | Grok 4.5 | 12.4% ±2.6 | high, Grok Build | xAI | Jul 2026 | Jul 2026 | Official leaderboard |
| 27 | | 11.2% ±2.5 | high, mini-SWE-agent | SWE-agent | Aug 2026 | Aug 2026 | Official leaderboard |
| 28 | | 7.27% ±2.7 | none, mini-swe-agent | SWE-agent | Jun 2026 | Jun 2026 | Official leaderboard |
| 29 | Beam 1.0 | 6.36% ±1.7 | none, mini-swe-agent | SWE-agent | Oct 2026 | Oct 2026 | Official leaderboard |
| 30 | | 2.73% ±1.7 | high, Antigravity CLI | Feb 2026 | Feb 2026 | Official leaderboard | |
| 31 | GPT-5.4 Mini | 1.82% ±1.3 | xhigh, Codex | OpenAI | Mar 2026 | Mar 2026 | Official leaderboard |
| 32 | | 0.91% ±0.9 | none, mini-swe-agent | SWE-agent | Jul 2026 | Jul 2026 | Official leaderboard |
| 33 | | 0.30% ±0.6 | none, mini-swe-agent | SWE-agent | Oct 2026 | Oct 2026 | Official leaderboard |
| 34 | | 0% | none, mini-swe-agent | SWE-agent | Jul 2026 | Jul 2026 | Official leaderboard |
| # | Model | Score ± 95% CI | Setting | Agent by | Released | Run on | Source |
|---|---|---|---|---|---|---|---|
| 1 | MiMo-V2.6 Pro | 27% ±3.6 | none, mini-swe-agent | SWE-agent | Sep 2026 | Sep 2026 | Official leaderboard |
| 2 | | 21.8% ±3.4 | none, mini-swe-agent | SWE-agent | Sep 2026 | Sep 2026 | Official leaderboard |
| 3 | | 19.1% ±3.4 | high, mini-SWE-agent | SWE-agent | Sep 2026 | Sep 2026 | Official leaderboard |
| 4 | MiMo-V2.6 Flash | 16.1% ±3.4 | none, mini-swe-agent | SWE-agent | Sep 2026 | Sep 2026 | Official leaderboard |
| 5 | | 11.2% ±2.5 | high, mini-SWE-agent | SWE-agent | Aug 2026 | Aug 2026 | Official leaderboard |
| 6 | | 7.27% ±2.7 | none, mini-swe-agent | SWE-agent | Jun 2026 | Jun 2026 | Official leaderboard |
| 7 | Beam 1.0 | 6.36% ±1.7 | none, mini-swe-agent | SWE-agent | Oct 2026 | Oct 2026 | Official leaderboard |
| 8 | | 0.91% ±0.9 | none, mini-swe-agent | SWE-agent | Jul 2026 | Jul 2026 | Official leaderboard |
| 9 | | 0.30% ±0.6 | none, mini-swe-agent | SWE-agent | Oct 2026 | Oct 2026 | Official leaderboard |
| 10 | | 0% | none, mini-swe-agent | SWE-agent | Jul 2026 | Jul 2026 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Sonnet 5.5 | 70.6% | Sep 2026 | Lab model card | |
| 2 | Claude Fable 5.2 | 67.6% | max effort | Nov 2026 | Lab model card |
| 3 | Claude Opus 5.5 | 66.4% | xhigh effort | Sep 2026 | Lab model card |
| 4 | Kimi K3.1 Pro | 65.7% | Oct 2026 | Lab model card | |
| 5 | 65.2% | Oct 2026 | Lab model card | ||
| 6 | GPT-6 Astra | 58.2% | max, Codex | Sep 2026 | Official leaderboard |
| 7 | GPT-6.1 Sol | 58.2% | max, Codex | Sep 2026 | Official leaderboard |
| 8 | Claude Fable 5.1 | 57.9% | max, Claude Code | Sep 2026 | Official leaderboard |
| 9 | 57.4% | Oct 2026 | Lab model card | ||
| 10 | 57.1% | Oct 2026 | Lab model card | ||
| 11 | Claude Opus 5 | 53.9% | xhigh, Claude Code | Jul 2026 | Official leaderboard |
| 12 | 52% | Oct 2026 | Lab model card | ||
| 13 | GPT-6.1 Terra | 51.8% | max, Codex | Oct 2026 | Official leaderboard |
| 14 | GPT-6 Sol | 49.4% | max, Codex | Sep 2026 | Official leaderboard |
| 15 | 48.5% | xhigh effort | Nov 2026 | Lab model card | |
| 16 | 46% | Oct 2026 | Lab model card | ||
| 17 | Claude Fable 5 | 44.5% | max, Claude Code | Jun 2026 | Official leaderboard |
| 18 | 44.4% | Nov 2026 | Lab model card | ||
| 19 | 42.3% | Oct 2026 | Lab model card | ||
| 20 | 41% | Oct 2026 | Lab model card | ||
| 21 | 40.9% | max effort | Nov 2026 | Lab model card | |
| 22 | Claude Haiku 5.5 | 40% | max, Claude Code | Oct 2026 | Official leaderboard |
| 23 | 38.5% | Nov 2026 | Lab model card | ||
| 24 | 38.1% | Oct 2026 | Lab model card | ||
| 25 | Grok 4.7 | 38% | Sep 2026 | Lab model card | |
| 26 | GPT-5.6 Sol | 37.3% | max, Codex | Jul 2026 | Official leaderboard |
| 27 | MiMo-V2.6 Pro | 34.9% | Sep 2026 | Lab model card | |
| 28 | 33.3% | Sep 2026 | Lab model card | ||
| 29 | 31.2% | Sep 2026 | Lab model card | ||
| 30 | MiMo-V2.6 Flash | 28.8% | Sep 2026 | Lab model card | |
| 31 | 28.3% | Oct 2026 | Lab model card | ||
| 32 | SWE-2 | 27.3% | Sep 2026 | Lab model card | |
| 33 | Claude Opus 4.8 | 23.6% | max, Claude Code | May 2026 | Official leaderboard |
| 34 | 21.8% | none, mini-swe-agent | Sep 2026 | Official leaderboard | |
| 35 | GPT-5.6 Terra | 21.5% | max, Codex | Jul 2026 | Official leaderboard |
| 36 | Grok 4.6 | 20.3% | high, Grok Build | Aug 2026 | Official leaderboard |
| 37 | SWE-2 Flash | 20% | Nov 2026 | Lab model card | |
| 38 | 19.1% | Sep 2026 | Lab model card | ||
| 39 | GPT-5.6 Luna | 17.3% | max, Codex | Jul 2026 | Official leaderboard |
| 40 | GPT-6 Luna | 16.4% | max, Codex | Sep 2026 | Official leaderboard |
| 41 | 14.6% | xhigh, Muse Code | Sep 2026 | Official leaderboard | |
| 42 | Claude Sonnet 5 | 12.4% | max, Claude Code | Jun 2026 | Official leaderboard |
| 43 | Grok 4.5 | 12.4% | high, Grok Build | Jul 2026 | Official leaderboard |
| 44 | 11.2% | high, mini-SWE-agent | Aug 2026 | Official leaderboard | |
| 45 | 7.27% | none, mini-swe-agent | Jun 2026 | Official leaderboard | |
| 46 | Beam 1.0 | 6.36% | none, mini-swe-agent | Oct 2026 | Official leaderboard |
| 47 | 5.60% | Nov 2026 | Lab model card | ||
| 48 | 2.73% | high, Antigravity CLI | Feb 2026 | Official leaderboard | |
| 49 | GPT-5.4 Mini | 1.82% | xhigh, Codex | Mar 2026 | Official leaderboard |
| 50 | 1.00% | Oct 2026 | Lab model card | ||
| 51 | 0.91% | none, mini-swe-agent | Jul 2026 | Official leaderboard | |
| 52 | 0% | none, mini-swe-agent | Jul 2026 | Official leaderboard |
Labs report scores for 31 models in their cards. Switch the scores above to rank them together.
Pareto: accuracy against time
Each point is one agent, model and effort. The board plots total run time; this plots the mean time per trial, the same frontier at a fixed trial count. The line joins the runs that no other run beats on both measures. We redrew this chart from the numbers on the official leaderboard.
| Model | Setting | Accuracy | Mean time per trial |
|---|---|---|---|
| Claude Opus 5.5 | max, Claude Code | 64.9% | 4,790 s |
| Claude Sonnet 5.5 | max, Claude Code | 61.8% | 7,432 s |
| Claude Code + Kimi K3.1 Pro | max, Claude Code | 60.9% | 4,047 s |
| GPT-6 Astra | max, Codex | 58.2% | 2,796 s |
| GPT-6.1 Sol | max, Codex | 58.2% | 3,177 s |
| GPT-6 Astra | high, Codex | 57.9% | 2,114 s |
| GPT-6 Astra | xhigh, Codex | 57.9% | 2,209 s |
| Claude Fable 5.1 | xhigh, Claude Code | 57.9% | 3,202 s |
| Claude Fable 5.1 | max, Claude Code | 57.9% | 3,894 s |
| high, Antigravity CLI | 54.9% | 3,895 s | |
| Claude Fable 5.1 | high, Claude Code | 54.6% | 3,018 s |
| GPT-6 Astra | medium, Codex | 54.2% | 1,886 s |
| Claude Fable 5.1 | medium, Claude Code | 53.9% | 2,528 s |
| Claude Opus 5 | xhigh, Claude Code | 53.9% | 4,515 s |
| GPT-6.1 Terra | max, Codex | 51.8% | 2,291 s |
| Claude Opus 5 | max, Claude Code | 51.8% | 4,793 s |
| GPT-6 Astra | low, Codex | 50.6% | 1,684 s |
| Claude Opus 5 | high, Claude Code | 50.3% | 3,822 s |
| GPT-6 Sol | max, Codex | 49.4% | 2,662 s |
| xhigh, Muse Code | 47% | 2,828 s | |
| Claude Opus 5 | medium, Claude Code | 44.9% | 3,293 s |
| Claude Fable 5 | max, Claude Code | 44.6% | 4,203 s |
| Claude Fable 5.1 | low, Claude Code | 43.3% | 2,291 s |
| Claude Code + GLM-5.3 | max, Claude Code | 41.8% | 5,831 s |
| Claude Haiku 5.5 | max, Claude Code | 40% | 4,059 s |
| Claude Code + DeepSeek V4.1 Flash 1017 | max, Claude Code | 40% | 5,030 s |
| Claude Code + Tencent Hy4 | max, Claude Code | 39.1% | 4,882 s |
| Grok 4.7 | xhigh, Grok Build | 37.6% | 5,701 s |
| GPT-5.6 Sol | max, Codex | 37.3% | 2,388 s |
| Claude Code + GLM-5.3-Flash | max, Claude Code | 36.7% | 6,558 s |
| Claude Code + GLM-5.3-Flash | none, Claude Code | 35.8% | 6,210 s |
| Claude Opus 5 | low, Claude Code | 34.9% | 2,947 s |
| Claude Code + Mistral Large 4 | max, Claude Code | 27.9% | 5,229 s |
| MiMo-V2.6 Pro | none, mini-swe-agent | 27% | 5,265 s |
| Claude Code + Qwen3.8 Max (0902) | max, Claude Code | 27% | 9,953 s |
| Claude Opus 4.8 | max, Claude Code | 23.6% | 5,163 s |
| Claude Code + Kimi K3 | max, Claude Code | 22.4% | 3,351 s |
| none, mini-swe-agent | 21.8% | 4,960 s | |
| GPT-5.6 Terra | max, Codex | 21.5% | 2,515 s |
| Grok 4.6 | high, Grok Build | 20.3% | 2,352 s |
| Claude Code + Tencent Hy4 preview | max, Claude Code | 19.4% | 6,967 s |
| high, mini-SWE-agent | 19.1% | 1,995 s | |
| GPT-5.6 Luna | max, Codex | 17.3% | 4,088 s |
| GPT-6 Luna | max, Codex | 16.4% | 2,284 s |
| MiMo-V2.6 Flash | none, mini-swe-agent | 16.1% | 5,472 s |
| xhigh, Muse Code | 14.6% | 4,342 s | |
| Grok 4.5 | high, Grok Build | 12.4% | 3,162 s |
| Claude Sonnet 5 | max, Claude Code | 12.4% | 6,510 s |
| high, mini-SWE-agent | 11.2% | 1,689 s | |
| none, mini-swe-agent | 7.3% | 3,507 s | |
| Claude Code + DeepSeek V4 Pro 0813 | max, Claude Code | 6.7% | 3,140 s |
| Beam 1.0 | none, mini-swe-agent | 6.4% | 1,440 s |
| high, Antigravity CLI | 2.7% | 4,583 s | |
| GPT-5.4 Mini | xhigh, Codex | 1.8% | 1,849 s |
| none, mini-swe-agent | 0.9% | 475.1 s | |
| none, mini-swe-agent | 0.3% | 1,781 s | |
| none, mini-swe-agent | 0% | 1,403 s |
Pareto: accuracy against time
Each point is one agent, model and effort. The board plots total run time; this plots the mean time per trial, the same frontier at a fixed trial count. The line joins the runs that no other run beats on both measures. We redrew this chart from the numbers on the official leaderboard.
| Model | Setting | Accuracy | Mean time per trial |
|---|---|---|---|
| Claude Opus 5.5 | max, Claude Code | 64.9% | 4,790 s |
| Claude Sonnet 5.5 | max, Claude Code | 61.8% | 7,432 s |
| GPT-6 Astra | max, Codex | 58.2% | 2,796 s |
| GPT-6.1 Sol | max, Codex | 58.2% | 3,177 s |
| GPT-6 Astra | high, Codex | 57.9% | 2,114 s |
| GPT-6 Astra | xhigh, Codex | 57.9% | 2,209 s |
| Claude Fable 5.1 | xhigh, Claude Code | 57.9% | 3,202 s |
| Claude Fable 5.1 | max, Claude Code | 57.9% | 3,894 s |
| high, Antigravity CLI | 54.9% | 3,895 s | |
| Claude Fable 5.1 | high, Claude Code | 54.6% | 3,018 s |
| GPT-6 Astra | medium, Codex | 54.2% | 1,886 s |
| Claude Fable 5.1 | medium, Claude Code | 53.9% | 2,528 s |
| Claude Opus 5 | xhigh, Claude Code | 53.9% | 4,515 s |
| GPT-6.1 Terra | max, Codex | 51.8% | 2,291 s |
| Claude Opus 5 | max, Claude Code | 51.8% | 4,793 s |
| GPT-6 Astra | low, Codex | 50.6% | 1,684 s |
| Claude Opus 5 | high, Claude Code | 50.3% | 3,822 s |
| GPT-6 Sol | max, Codex | 49.4% | 2,662 s |
| xhigh, Muse Code | 47% | 2,828 s | |
| Claude Opus 5 | medium, Claude Code | 44.9% | 3,293 s |
| Claude Fable 5 | max, Claude Code | 44.6% | 4,203 s |
| Claude Fable 5.1 | low, Claude Code | 43.3% | 2,291 s |
| Claude Haiku 5.5 | max, Claude Code | 40% | 4,059 s |
| Grok 4.7 | xhigh, Grok Build | 37.6% | 5,701 s |
| GPT-5.6 Sol | max, Codex | 37.3% | 2,388 s |
| Claude Opus 5 | low, Claude Code | 34.9% | 2,947 s |
| MiMo-V2.6 Pro | none, mini-swe-agent | 27% | 5,265 s |
| Claude Opus 4.8 | max, Claude Code | 23.6% | 5,163 s |
| none, mini-swe-agent | 21.8% | 4,960 s | |
| GPT-5.6 Terra | max, Codex | 21.5% | 2,515 s |
| Grok 4.6 | high, Grok Build | 20.3% | 2,352 s |
| high, mini-SWE-agent | 19.1% | 1,995 s | |
| GPT-5.6 Luna | max, Codex | 17.3% | 4,088 s |
| GPT-6 Luna | max, Codex | 16.4% | 2,284 s |
| MiMo-V2.6 Flash | none, mini-swe-agent | 16.1% | 5,472 s |
| xhigh, Muse Code | 14.6% | 4,342 s | |
| Grok 4.5 | high, Grok Build | 12.4% | 3,162 s |
| Claude Sonnet 5 | max, Claude Code | 12.4% | 6,510 s |
| high, mini-SWE-agent | 11.2% | 1,689 s | |
| none, mini-swe-agent | 7.3% | 3,507 s | |
| Beam 1.0 | none, mini-swe-agent | 6.4% | 1,440 s |
| high, Antigravity CLI | 2.7% | 4,583 s | |
| GPT-5.4 Mini | xhigh, Codex | 1.8% | 1,849 s |
| none, mini-swe-agent | 0.9% | 475.1 s | |
| none, mini-swe-agent | 0.3% | 1,781 s | |
| none, mini-swe-agent | 0% | 1,403 s |
Pareto: accuracy against time
Each point is one agent, model and effort. The board plots total run time; this plots the mean time per trial, the same frontier at a fixed trial count. The line joins the runs that no other run beats on both measures. We redrew this chart from the numbers on the official leaderboard.
| Model | Setting | Accuracy | Mean time per trial |
|---|---|---|---|
| MiMo-V2.6 Pro | none, mini-swe-agent | 27% | 5,265 s |
| none, mini-swe-agent | 21.8% | 4,960 s | |
| high, mini-SWE-agent | 19.1% | 1,995 s | |
| MiMo-V2.6 Flash | none, mini-swe-agent | 16.1% | 5,472 s |
| high, mini-SWE-agent | 11.2% | 1,689 s | |
| none, mini-swe-agent | 7.3% | 3,507 s | |
| Beam 1.0 | none, mini-swe-agent | 6.4% | 1,440 s |
| none, mini-swe-agent | 0.9% | 475.1 s | |
| none, mini-swe-agent | 0.3% | 1,781 s | |
| none, mini-swe-agent | 0% | 1,403 s |
The best score, 64.8%, costs $14 a task
Runs on the cost frontier score higher than any run that's cheaper. Claude Code + Kimi K3.1 Pro at max comes within 3.9 points of the best for $3.29 a task, 4 times cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.
Source: Official Terminal-Bench 4.0 leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| Claude Opus 5.5 | max | Claude Code | 64.8% | $14 | 269,135 |
| Claude Sonnet 5.5 | max | Claude Code | 61.8% | $22 | 565,388 |
| Claude Code + Kimi K3.1 Pro | max | Claude Code | 60.9% | $3.29 | 80,956 |
| GPT-6 Astra | max | Codex | 58.2% | $9.90 | 72,694 |
| GPT-6.1 Sol | max | Codex | 58.2% | $1.92 | 94,892 |
| Claude Fable 5.1 | max | Claude Code | 57.9% | $19 | 191,277 |
| Claude Fable 5.1 | xhigh | Claude Code | 57.9% | $15 | 152,809 |
| GPT-6 Astra | xhigh | Codex | 57.9% | $7.12 | 45,304 |
| GPT-6 Astra | high | Codex | 57.9% | $6.88 | 41,527 |
| high | Antigravity CLI | 54.9% | $3.36 | 162,988 | |
| Claude Fable 5.1 | high | Claude Code | 54.5% | $12 | 113,421 |
| GPT-6 Astra | medium | Codex | 54.2% | $5.80 | 32,638 |
| Claude Opus 5 | xhigh | Claude Code | 53.9% | $18 | 179,281 |
| Claude Fable 5.1 | medium | Claude Code | 53.9% | $8.59 | 78,763 |
| Claude Opus 5 | max | Claude Code | 51.8% | $18 | 200,037 |
| GPT-6.1 Terra | max | Codex | 51.8% | $2.65 | 100,138 |
| GPT-6 Astra | low | Codex | 50.6% | $4.72 | 24,207 |
| Claude Opus 5 | high | Claude Code | 50.3% | $14 | 144,242 |
| GPT-6 Sol | max | Codex | 49.4% | $4.40 | 92,642 |
| xhigh | Muse Code | 47% | $7.43 | 129,324 | |
| Claude Opus 5 | medium | Claude Code | 44.9% | $9.67 | 101,450 |
| Claude Fable 5 | max | Claude Code | 44.5% | $22 | 177,636 |
| Claude Fable 5.1 | low | Claude Code | 43.3% | $7.15 | 60,409 |
| Claude Code + GLM-5.3 | max | Claude Code | 41.8% | $8.27 | 208,061 |
| Claude Haiku 5.5 | max | Claude Code | 40% | $2.89 | 386,483 |
| Claude Code + DeepSeek V4.1 Flash 1017 | max | Claude Code | 40% | $0.56 | 497,265 |
| Claude Code + Tencent Hy4 | max | Claude Code | 39.1% | $1.05 | 368,811 |
| Grok 4.7 | xhigh | Grok Build | 37.6% | $11 | 69,627 |
| GPT-5.6 Sol | max | Codex | 37.3% | $7.70 | 71,065 |
| Claude Code + GLM-5.3-Flash | max | Claude Code | 36.7% | $1.14 | 459,702 |
| Claude Code + GLM-5.3-Flash | none | Claude Code | 35.8% | $0.36 | 135,014 |
| Claude Opus 5 | low | Claude Code | 34.9% | $7.25 | 72,229 |
| Claude Code + Mistral Large 4 | max | Claude Code | 27.9% | $2.18 | 253,650 |
| MiMo-V2.6 Pro | none | mini-swe-agent | 27% | $0.86 | 245,849 |
| Claude Code + Qwen3.8 Max (0902) | max | Claude Code | 27% | $14 | 252,708 |
| Claude Opus 4.8 | max | Claude Code | 23.6% | $20 | 269,131 |
| Claude Code + Kimi K3 | max | Claude Code | 22.4% | $5.82 | 195,427 |
| none | mini-swe-agent | 21.8% | $14 | 187,695 | |
| GPT-5.6 Terra | max | Codex | 21.5% | $5.25 | 100,681 |
| Grok 4.6 | high | Grok Build | 20.3% | $11 | 98,843 |
| Claude Code + Tencent Hy4 preview | max | Claude Code | 19.4% | $1.99 | 309,296 |
| high | mini-SWE-agent | 19.1% | $5.54 | 206,232 | |
| GPT-5.6 Luna | max | Codex | 17.3% | $1.05 | 185,705 |
| GPT-6 Luna | max | Codex | 16.4% | $0.22 | 137,851 |
| MiMo-V2.6 Flash | none | mini-swe-agent | 16.1% | $0.59 | 200,090 |
| xhigh | Muse Code | 14.6% | 265,112 | ||
| Claude Sonnet 5 | max | Claude Code | 12.4% | $29 | 353,330 |
| Grok 4.5 | high | Grok Build | 12.4% | $6.35 | 98,149 |
| high | mini-SWE-agent | 11.2% | $3.82 | 157,982 | |
| none | mini-swe-agent | 7.27% | $3.48 | 234,421 | |
| Claude Code + DeepSeek V4 Pro 0813 | max | Claude Code | 6.67% | $2.20 | 245,205 |
| Beam 1.0 | none | mini-swe-agent | 6.36% | $0.71 | 64,523 |
| high | Antigravity CLI | 2.73% | $5.97 | 79,607 | |
| GPT-5.4 Mini | xhigh | Codex | 1.82% | $2.04 | 169,597 |
| none | mini-swe-agent | 0.91% | $0.15 | 20,104 | |
| none | mini-swe-agent | 0.30% | $0.51 | 159,709 | |
| none | mini-swe-agent | 0% | $3.06 | 39,308 |
The best score, 64.8%, costs $14 a task
Runs on the cost frontier score higher than any run that's cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.
Source: Official Terminal-Bench 4.0 leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| Claude Opus 5.5 | max | Claude Code | 64.8% | $14 | 269,135 |
| Claude Sonnet 5.5 | max | Claude Code | 61.8% | $22 | 565,388 |
| GPT-6 Astra | max | Codex | 58.2% | $9.90 | 72,694 |
| GPT-6.1 Sol | max | Codex | 58.2% | $1.92 | 94,892 |
| Claude Fable 5.1 | max | Claude Code | 57.9% | $19 | 191,277 |
| Claude Fable 5.1 | xhigh | Claude Code | 57.9% | $15 | 152,809 |
| GPT-6 Astra | xhigh | Codex | 57.9% | $7.12 | 45,304 |
| GPT-6 Astra | high | Codex | 57.9% | $6.88 | 41,527 |
| high | Antigravity CLI | 54.9% | $3.36 | 162,988 | |
| Claude Fable 5.1 | high | Claude Code | 54.5% | $12 | 113,421 |
| GPT-6 Astra | medium | Codex | 54.2% | $5.80 | 32,638 |
| Claude Opus 5 | xhigh | Claude Code | 53.9% | $18 | 179,281 |
| Claude Fable 5.1 | medium | Claude Code | 53.9% | $8.59 | 78,763 |
| Claude Opus 5 | max | Claude Code | 51.8% | $18 | 200,037 |
| GPT-6.1 Terra | max | Codex | 51.8% | $2.65 | 100,138 |
| GPT-6 Astra | low | Codex | 50.6% | $4.72 | 24,207 |
| Claude Opus 5 | high | Claude Code | 50.3% | $14 | 144,242 |
| GPT-6 Sol | max | Codex | 49.4% | $4.40 | 92,642 |
| xhigh | Muse Code | 47% | $7.43 | 129,324 | |
| Claude Opus 5 | medium | Claude Code | 44.9% | $9.67 | 101,450 |
| Claude Fable 5 | max | Claude Code | 44.5% | $22 | 177,636 |
| Claude Fable 5.1 | low | Claude Code | 43.3% | $7.15 | 60,409 |
| Claude Haiku 5.5 | max | Claude Code | 40% | $2.89 | 386,483 |
| Grok 4.7 | xhigh | Grok Build | 37.6% | $11 | 69,627 |
| GPT-5.6 Sol | max | Codex | 37.3% | $7.70 | 71,065 |
| Claude Opus 5 | low | Claude Code | 34.9% | $7.25 | 72,229 |
| MiMo-V2.6 Pro | none | mini-swe-agent | 27% | $0.86 | 245,849 |
| Claude Opus 4.8 | max | Claude Code | 23.6% | $20 | 269,131 |
| none | mini-swe-agent | 21.8% | $14 | 187,695 | |
| GPT-5.6 Terra | max | Codex | 21.5% | $5.25 | 100,681 |
| Grok 4.6 | high | Grok Build | 20.3% | $11 | 98,843 |
| high | mini-SWE-agent | 19.1% | $5.54 | 206,232 | |
| GPT-5.6 Luna | max | Codex | 17.3% | $1.05 | 185,705 |
| GPT-6 Luna | max | Codex | 16.4% | $0.22 | 137,851 |
| MiMo-V2.6 Flash | none | mini-swe-agent | 16.1% | $0.59 | 200,090 |
| xhigh | Muse Code | 14.6% | 265,112 | ||
| Claude Sonnet 5 | max | Claude Code | 12.4% | $29 | 353,330 |
| Grok 4.5 | high | Grok Build | 12.4% | $6.35 | 98,149 |
| high | mini-SWE-agent | 11.2% | $3.82 | 157,982 | |
| none | mini-swe-agent | 7.27% | $3.48 | 234,421 | |
| Beam 1.0 | none | mini-swe-agent | 6.36% | $0.71 | 64,523 |
| high | Antigravity CLI | 2.73% | $5.97 | 79,607 | |
| GPT-5.4 Mini | xhigh | Codex | 1.82% | $2.04 | 169,597 |
| none | mini-swe-agent | 0.91% | $0.15 | 20,104 | |
| none | mini-swe-agent | 0.30% | $0.51 | 159,709 | |
| none | mini-swe-agent | 0% | $3.06 | 39,308 |
The best score, 27%, costs $0.86 a task
Runs on the cost frontier score higher than any run that's cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.
Source: Official Terminal-Bench 4.0 leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| MiMo-V2.6 Pro | none | mini-swe-agent | 27% | $0.86 | 245,849 |
| none | mini-swe-agent | 21.8% | $14 | 187,695 | |
| high | mini-SWE-agent | 19.1% | $5.54 | 206,232 | |
| MiMo-V2.6 Flash | none | mini-swe-agent | 16.1% | $0.59 | 200,090 |
| high | mini-SWE-agent | 11.2% | $3.82 | 157,982 | |
| none | mini-swe-agent | 7.27% | $3.48 | 234,421 | |
| Beam 1.0 | none | mini-swe-agent | 6.36% | $0.71 | 64,523 |
| none | mini-swe-agent | 0.91% | $0.15 | 20,104 | |
| none | mini-swe-agent | 0.30% | $0.51 | 159,709 | |
| none | mini-swe-agent | 0% | $3.06 | 39,308 |
4 models have held number one on the official leaderboard since its release in August 2026 5 models have held number one with claims included since its release in August 2026
Lab claims count from the day the card came out, independent runs from the model’s release. We draw one row each for the benchmark’s own leaderboard and what labs claim in their cards.
Sources: Official Terminal-Bench 4.0 leaderboard and labs’ model cards
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Sources: Official Terminal-Bench 4.0 leaderboard and labs’ model cards
Sources: Official Terminal-Bench 4.0 leaderboard and labs’ model cards
18 labs put it in a launch post in the last six months
Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| Nov 20, 2026 | 5.6 | Terminal Bench v4.0 (mini-swe-agent v2.4.6) | |
| Nov 15, 2026 | 48.5 | Agentic terminal coding, Terminal-Bench 4.0 (Xhigh effort) | |
| Nov 9, 2026 | 40.9 | Terminal-Bench 4.0, best published harness, Muse Ember max reasoning | |
| Nov 4, 2026 | 44.4 | Terminal Bench 4.0 | |
| Nov 4, 2026 | SWE-2 Flash | 20 | Terminal-Bench 4.0 |
| Nov 2, 2026 | 38.5 | Terminal Bench v4.0 | |
| Oct 29, 2026 | 41 | Terminal-Bench 4.0 (Artificial Analysis Coding Agent Index run) | |
| Oct 28, 2026 | 65.2 | Terminal-Bench 4.0 (AA) | |
| Oct 26, 2026 | GPT-6.1 Terra | 50.3 | Terminal-Bench 4.0, maximum reasoning effort |
| Oct 24, 2026 | Kimi K3.1 Pro | 65.7 | Terminal-Bench 4.0 (Claude Code) |
| Oct 19, 2026 | 38.1 | Terminal Bench 4.0 | |
| Oct 17, 2026 | 42.3 | Terminal-Bench 4.0 | |
| Oct 15, 2026 | 1 | Terminal Bench 4 [offline] | |
| Oct 13, 2026 | 46 | Terminal-Bench-4.0 (LingCode) | |
| Oct 13, 2026 | 57.4 | Terminal-bench 4.0 | |
| Oct 12, 2026 | 52 | Terminal-Bench 4.0-AA | |
| Oct 12, 2026 | 57.1 | Terminal-Bench 4.0-AA | |
| Oct 7, 2026 | Claude Haiku 5.5 | 39.2 | Agentic coding Terminal-Bench 4.0 |
| Oct 6, 2026 | 28.3 | Coding - Terminal Bench 4.0: AA - Terminal-Bench 4 (chart 28; text 28.3%) | |
| Sep 28, 2026 | Claude Sonnet 5.5 | 70.6 | Agentic coding Terminal-Bench 4.0 |
| Sep 22, 2026 | MiMo-V2.6 Pro | 34.9 | Terminal Bench 4.0 |
| Sep 22, 2026 | Claude Opus 5.5 | 66.4 | Agentic coding Terminal-Bench 4.0 (xhigh effort) |
| Sep 21, 2026 | MiMo-V2.6 Flash | 28.8 | Terminal Bench 4.0 |
| Sep 21, 2026 | Grok 4.7 | 37.6 | Terminal-Bench 4.0 (Multi-hour terminal work) |
| Sep 20, 2026 | 33.3 | Terminal-Bench v4 | |
| Sep 10, 2026 | SWE-2 | 27.3 | Terminal-Bench 4.0 |
| Sep 10, 2026 | 31.2 | Terminal-Bench 4.0 (Pass@1) | |
| Sep 3, 2026 | GPT-6 Astra | 57.9 | Terminal-Bench 4.0 |
| Sep 2, 2026 | 19.1 | Terminal-bench 4.0 |
15 system cards report it, from 7 labs
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| Nov 20, 2026 | | 5.6 | Terminal Bench v4.0 (mini-swe-agent v2.4.6) | Capabilities |
| Nov 10, 2026 | | 65.2 | Terminal-Bench 4.0 (AA) (results table) | Capabilities |
| Nov 9, 2026 | | 40.9 | Terminal-Bench 4.0, best published harness, Muse Ember max reasoning | Capabilities |
| Nov 9, 2026 | Claude Fable 5.2 system card | 67.6 | Terminal-Bench 4.0, safeguards enabled, Claude Code --bare, max effort, no internet access, 10 trials per task. Mythos-only score 70.5% excluded (Section 8.5) | Capabilities |
| Oct 13, 2026 | | 57.4 | Terminal-bench 4.0 (results table, p.5) | Capabilities |
| Oct 12, 2026 | | 52 | Terminal-Bench 4.0-AA accuracy from Artificial Analysis, Muse Wonder (max) (capabilities table image, page 3) | Capabilities |
| Oct 12, 2026 | | 57.1 | Terminal-Bench 4.0-AA accuracy from Artificial Analysis, Muse Wonder Full (max) (capabilities table image, page 3) | Capabilities |
| Oct 7, 2026 | Claude Haiku 5.5 system card | 39.2 | Terminal-Bench 4.0, max effort, safeguards on with no fallback, no internet egress (8.4) | Capabilities |
| Sep 28, 2026 | Claude Sonnet 5.5 system card | 70.6 | Terminal-Bench 4.0, max effort with safeguards and fallbacks, five trials per task (8.5) | Capabilities |
| Sep 22, 2026 | MiMo-V2.6 Pro technical report | 34.9 | Terminal Bench 4.0 (Table 3) | Capabilities |
| Sep 22, 2026 | Claude Opus 5.5 system card | 66.4 | Terminal-Bench 4.0 at xhigh effort, the setting the summary table marks (64.8% at max), Claude Code --bare mode, safeguards with fallback, five trials per task (Table 8.1.A, 8.5) | Capabilities |
| Sep 21, 2026 | Grok 4.7 model card | 38 | Terminal-Bench 4.0, task success rate, xhigh, Grok Build harness, run by Harbor (2.3) | Capabilities |
| Sep 10, 2026 | | 31.2 | Terminal-Bench 4.0 (Pass@1) (Table 3) | Capabilities |
| Sep 2, 2026 | | 19.1 | Terminal-bench 4.0 (results table, p.5) | Capabilities |
| Sep 1, 2026 | Claude Fable 5.1 system card | 55.8 | Terminal-Bench 4.0, Claude Code --bare mode, max effort, 15 trials per task; Table 8.1.A rounds to 56% (Mythos 5.1 61%) (8.6) | Capabilities |
The lab's number comes out ahead in 8 of 12 pairs that differ
Each score a lab reported for its own model, beside the same model's best score on the leaderboard. Gaps mostly come from different harnesses, effort levels and task subsets. 1 of them match, which usually means one side copied the other. Every benchmark.
| Model | Lab says | Board says | Gap |
|---|---|---|---|
| MiMo-V2.6 Flash | 28.8% Terminal Bench 4.0 | 16.1% Leaderboard, none, mini-swe-agent | +13 pts |
| Claude Sonnet 5.5 | 70.6% Agentic coding Terminal-Bench 4.0 | 61.8% Leaderboard, max, Claude Code | +8.8 pts |
| MiMo-V2.6 Pro | 34.9% Terminal Bench 4.0 | 27% Leaderboard, none, mini-swe-agent | +7.9 pts |
| | 52% Terminal-Bench 4.0-AA | 47% Leaderboard, xhigh, Muse Code | +5.0 pts |
| | 57.4% Terminal-bench 4.0 | 54.9% Leaderboard, high, Antigravity CLI | +2.5 pts |
| Claude Fable 5.1 | 55.8% Terminal-Bench 4.0, Claude Code --bare mode, max effort, 15 trials per task; Table 8.1.A rounds to 56% (Mythos 5.1 61%) (8.6) | 57.9% Leaderboard, max, Claude Code | −2.1 pts |
| Claude Opus 5.5 | 66.4% Agentic coding Terminal-Bench 4.0 (xhigh effort) | 64.8% Leaderboard, max, Claude Code | +1.6 pts |
| GPT-6.1 Terra | 50.3% Terminal-Bench 4.0, maximum reasoning effort | 51.8% Leaderboard, max, Codex | −1.5 pts |
| Claude Haiku 5.5 | 39.2% Agentic coding Terminal-Bench 4.0 | 40% Leaderboard, max, Claude Code | −0.8 pts |
| | 1.00% Terminal Bench 4 [offline] | 0.30% Leaderboard, none, mini-swe-agent | +0.7 pts |
| Grok 4.7 | 38% Terminal-Bench 4.0, task success rate, xhigh, Grok Build harness, run by Harbor (2.3) | 37.6% Leaderboard, xhigh, Grok Build | +0.4 pts |
| GPT-6 Astra | 57.9% Terminal-Bench 4.0 | 58.2% Leaderboard, max, Codex | −0.3 pts |
| | 19.1% Terminal-bench 4.0 | 19.1% Leaderboard, high, mini-SWE-agent | Same |
Versions
We switch the top row to each new version when it comes out. Open it for one row per version. An old version stays in play while people still test it, so whoever first takes it past 85% gets credit for closing it out.
Sources: Official leaderboards and boards copied by Epoch AI (CC BY 4.0)
More in Terminal agents
- SkillsBench In use 86-87 containerized expert tasks in 11 domains, run with and without Agent Skills. Verifier tests give pass rate and skill lift. GPT-5.5 66.5%
- Terminal-Bench Hard In use Agents complete 44 hard tasks from Terminal-Bench Core in the Terminus 2 harness. Artificial Analysis scores pass@1 averaged over 3 repeats.
Gemma 4 31B IT 36%
- Harbor-Index In use Agents solve about 80 hard tasks drawn from 29 benchmarks run through Harbor adapters, such as HLE, GSO and SWE-bench Pro. Each task keeps its source verifier. GPT-5.5 28.1%
- Terminal-Bench 2.1 Extended Not in model cards Agents complete long command-line tasks in containers, scored by verification tests. Mercor adds 99 new expert-written tasks to the 89 public ones and reports both scores.
Muse Wonder 54%
- Terminal-Bench Pro Not in model cards Agents solve 400 terminal tasks across eight domains. Harbor distributes the 200 public tasks. Alibaba keeps the other 200 for private evaluation. Claude Opus 4.5 51%
- o11y-bench Not in model cards Agents query metrics, logs and traces in a live Grafana stack, investigate incidents and fix dashboards. Grading checks claims against facts read from the same environment. Claude Opus 5.5 93.8%
Data audit
11 of 12 checks pass, 1 warning. Look first at the Lab claims check. 1 of 13 pairs differs by more than 10 points, the largest for MiMo-V2.6 Flash (+13 pts). Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 5 pass
- Pass Independent runs Scores from the official leaderboard (44 entries), launch posts (29 scores) and system cards (15 scores).
- Pass Models scored 52 models we track, plus 10 other entries on its leaderboard.
- Pass Newest score The newest is from November 2026, for Inkling 2 Mini.
- Pass Frontier models 9 of the top 10 have a score, led by Claude Fable 5.2 (#2).
- Pass Headroom The best is 70.6%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on tbench.ai: 57 rows for models we track at the last read.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 warning 1 pass
- Warning Lab claims 1 of 13 pairs differs by more than 10 points, the largest for MiMo-V2.6 Flash (+13 pts).
- Pass Known issues No published audit found problems.