Benchmark Almanac

Terminal-Bench 4.1

Copilot Fusion router 71.2% leads since November 2026 MiMo-V2.6 Pro 27% leads in mini-SWE-agent
Copilot Fusion router 71.2% leads since November 2026
In use
Version 4.1

The official leaderboard hasn’t scored a model released after GPT-6.2 Astra (November 2026). Labs report their own numbers for one newer model: Gemini 4 Neon at 65.2%.

The Terminal-Bench 4.0 tasks with hardened verifiers: 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 kept the 4.0 tasks and hardened the verifiers of 44 of them against reward hacking, then regraded the saved 4.0 runs. 162 trials changed score, and every model stayed within its earlier 95% interval.

Released
November 2026
Kind
Terminal tasks
Level
Expert
Scored
Checked automatically
Answers
Agent task
Tasks
All public
Measures
Capability
Language
English
In and out
Text, Code → Code, Actions
Interaction
Agentic
Environment
Terminal
Items from
Another benchmark
Run by
Anyone
In views
Agents
Strongest model tested
GPT-6.2 Astra #1 on the capability index
Last in a launch post
November 2026
Last model added
November 2026
Scores refreshed
November 18th, 2026
52
Entries on its own leaderboard, 42 models we track
2
Launch posts list it, from 1 lab
1
System card reports it, from 1 lab

Copilot Fusion leads with 71.2% Copilot Fusion leads with 71.2% MiMo-V2.6 Pro leads with 27% in mini-SWE-agent

Best score per entry from the benchmark's own leaderboard, read on November 18th, 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.

Copilot Fusion leads with 71.2%, 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.

  1. 1 Copilot Fusion max router 71.2%
  2. 2 Claude Opus 5.5 max 65.8%
  3. 3 Claude Fable 5.2 max 65.8%
  4. 4 Gemini 4 Carbon high 64.5%
  5. 5 Claude Sonnet 5.5 max 63.9%
  6. 6 GPT-6.2 Astra max 62.1%
  7. 7 GPT-6.2 Sol max 61.5%
  8. 8 GPT-6.1 Sol max 60.9%
  9. 9 GPT-6 Astra max 60.3%
  10. 10 Claude Code + Kimi K3.1 Pro max 59.7%
  11. 11 Claude Fable 5.1 xhigh 57.6%
  12. 12 Gemini 4 Hydrogen high 56.4%
  13. 13 Gemini 4 Argon high 55.5%
  14. 14 Claude Opus 5 xhigh 53.3%
  15. 15 GPT-6.1 Terra max 53.3%
  16. 16 GPT-6 Sol max 50.3%
  17. 17 Muse Wonder xhigh 47%
  18. 18 Claude Fable 5 max 44.9%
  19. 19 Claude Code + GLM-5.3 max 41.2%
  20. 20 Claude Haiku 5.5 max 40%
  21. 21 Grok 4.7 xhigh 38.8%
  22. 22 GPT-5.6 Sol max 38.5%
  23. 23 Claude Code + DeepSeek V4.1 Flash 1017 max 38.5%
  24. 24 Claude Code + Tencent Hy4 max 37.9%
  25. 25 Claude Code + GLM-5.3-Flash max 37%
  26. 26 Muse Ember xhigh 30.6%
  27. 27 Claude Code + Mistral Large 4 max 27.6%
  28. 28 Claude Code + Qwen3.8 Max (0902) max 27%
  29. 29 MiMo-V2.6 Pro none 27%
  30. 30 Claude Opus 4.8 max 23.6%
  31. 31 Claude Code + Kimi K3 max 23%
  32. 32 Ember-1 none 21.8%
  33. 33 GPT-5.6 Terra max 21.5%
  34. 34 Grok 4.6 high 19.7%
  35. 35 Claude Code + Tencent Hy4 preview max 19.1%
  36. 36 Gemini 3.8 Flash high 18.2%
  37. 37 GPT-5.6 Luna max 17.6%
  38. 38 MiMo-V2.6 Flash none 16.1%
  39. 39 GPT-6 Luna max 15.2%
  40. 40 Muse Spark 1.3 xhigh 14.8%
  41. 41 Inkling 2 Small xhigh 13%
  42. 42 Grok 4.5 high 12.4%
  43. 43 Gemini 3.7 Flash high 12.4%
  44. 44 Claude Sonnet 5 max 12.1%
  45. 45 MiniMax-M3 none 7.58%
  46. 46 Claude Code + DeepSeek V4 Pro 0813 max 6.67%
  47. 47 Beam 1.0 none 6.36%
  48. 48 Gemini 3.1 Pro high 2.73%
  49. 49 GPT-5.4 Mini xhigh 1.82%
  50. 50 Inkling-Small none 0.91%
  51. 51 Nemotron 3.5 Super VL none 0.30%
  52. 52 Inkling none 0%

Source: Official Terminal-Bench 4.1 leaderboard

Source: Official Terminal-Bench 4.1 leaderboard

Sources: Official Terminal-Bench 4.1 leaderboard and labs’ model cards

#EntryScore ± 95% CISettingAgent byReleasedRun onSource
1 Copilot Fusion router 71.2% ±2.9 max, GitHub Copilot GitHub Oct 2026 Nov 2026 Official leaderboard
2 Claude Opus 5.5 65.8% ±3.1 max, Claude Code Anthropic Sep 2026 Sep 2026 Official leaderboard
3 Claude Fable 5.2 65.8% ±2.9 max, Claude Code Anthropic Nov 2026 Nov 2026 Official leaderboard
4 Gemini 4 Carbon 64.5% ±3.2 high, Antigravity CLI Google Oct 2026 Oct 2026 Official leaderboard
5 Claude Sonnet 5.5 63.9% ±3 max, Claude Code Anthropic Sep 2026 Sep 2026 Official leaderboard
6 GPT-6.2 Astra 62.1% ±2.3 max, Codex OpenAI Nov 2026 Nov 2026 Official leaderboard
7 GPT-6.2 Sol 61.5% ±2.7 max, Codex OpenAI Nov 2026 Nov 2026 Official leaderboard
8 GPT-6.1 Sol 60.9% ±3 max, Codex OpenAI Sep 2026 Sep 2026 Official leaderboard
9 GPT-6 Astra 60.3% ±2.8 max, Codex OpenAI Sep 2026 Sep 2026 Official leaderboard
10 Claude Code + Kimi K3.1 Pro 59.7% ±4.2 max Anthropic Oct 2026 Oct 2026 Official leaderboard
11 Claude Fable 5.1 57.6% ±3.3 xhigh, Claude Code Anthropic Sep 2026 Sep 2026 Official leaderboard
12 Gemini 4 Hydrogen 56.4% ±3 high, Antigravity CLI Google Nov 2026 Nov 2026 Official leaderboard
13 Gemini 4 Argon 55.5% ±2.8 high, Antigravity CLI Google Sep 2026 Sep 2026 Official leaderboard
14 Claude Opus 5 53.3% ±3.1 xhigh, Claude Code Anthropic Jul 2026 Jul 2026 Official leaderboard
15 GPT-6.1 Terra 53.3% ±3.1 max, Codex OpenAI Oct 2026 Oct 2026 Official leaderboard
16 GPT-6 Sol 50.3% ±3.2 max, Codex OpenAI Sep 2026 Sep 2026 Official leaderboard
17 Muse Wonder 47% ±3.8 xhigh, Muse Code Meta Oct 2026 Oct 2026 Official leaderboard
18 Claude Fable 5 44.9% ±3.8 max, Claude Code Anthropic Jun 2026 Jun 2026 Official leaderboard
19 Claude Code + GLM-5.3 41.2% ±3.3 max Anthropic Aug 2026 Aug 2026 Official leaderboard
20 Claude Haiku 5.5 40% ±3.6 max, Claude Code Anthropic Oct 2026 Oct 2026 Official leaderboard
21 Grok 4.7 38.8% ±3.6 xhigh, Grok Build xAI Sep 2026 Sep 2026 Official leaderboard
22 GPT-5.6 Sol 38.5% ±3.8 max, Codex OpenAI Jul 2026 Jun 2026 Official leaderboard
23 Claude Code + DeepSeek V4.1 Flash 1017 38.5% ±3.8 max Anthropic Oct 2026 Oct 2026 Official leaderboard
24 Claude Code + Tencent Hy4 37.9% ±3.5 max Anthropic Nov 2026 Nov 2026 Official leaderboard
25 Claude Code + GLM-5.3-Flash 37% ±3.6 max Anthropic Aug 2026 Aug 2026 Official leaderboard
26 Muse Ember 30.6% ±3.8 xhigh, Muse Code Meta Nov 2026 Nov 2026 Official leaderboard
27 Claude Code + Mistral Large 4 27.6% ±3.9 max Anthropic Oct 2026 Oct 2026 Official leaderboard
28 Claude Code + Qwen3.8 Max (0902) 27% ±3.9 max Anthropic Sep 2026 Sep 2026 Official leaderboard
29 MiMo-V2.6 Pro 27% ±3.6 none, mini-swe-agent SWE-agent Sep 2026 Sep 2026 Official leaderboard
30 Claude Opus 4.8 23.6% ±3.6 max, Claude Code Anthropic May 2026 May 2026 Official leaderboard
31 Claude Code + Kimi K3 23% ±3.7 max Anthropic Jul 2026 Jul 2026 Official leaderboard
32 Ember-1 21.8% ±3.5 none, mini-swe-agent SWE-agent Sep 2026 Sep 2026 Official leaderboard
33 GPT-5.6 Terra 21.5% ±3.3 max, Codex OpenAI Jul 2026 Jun 2026 Official leaderboard
34 Grok 4.6 19.7% ±3.1 high, Grok Build xAI Aug 2026 Aug 2026 Official leaderboard
35 Claude Code + Tencent Hy4 preview 19.1% ±3.1 max Anthropic Aug 2026 Aug 2026 Official leaderboard
36 Gemini 3.8 Flash 18.2% ±3.4 high, mini-SWE-agent SWE-agent Sep 2026 Sep 2026 Official leaderboard
37 GPT-5.6 Luna 17.6% ±2.9 max, Codex OpenAI Jul 2026 Jun 2026 Official leaderboard
38 MiMo-V2.6 Flash 16.1% ±3.4 none, mini-swe-agent SWE-agent Sep 2026 Sep 2026 Official leaderboard
39 GPT-6 Luna 15.2% ±2.7 max, Codex OpenAI Sep 2026 Sep 2026 Official leaderboard
40 Muse Spark 1.3 14.8% ±3 xhigh, Muse Code Meta Sep 2026 Sep 2026 Official leaderboard
41 Inkling 2 Small 13% ±2.9 xhigh, mini-swe-agent SWE-agent Nov 2026 Nov 2026 Official leaderboard
42 Grok 4.5 12.4% ±2.6 high, Grok Build xAI Jul 2026 Jul 2026 Official leaderboard
43 Gemini 3.7 Flash 12.4% ±2.5 high, mini-SWE-agent SWE-agent Aug 2026 Aug 2026 Official leaderboard
44 Claude Sonnet 5 12.1% ±3 max, Claude Code Anthropic Jun 2026 Jun 2026 Official leaderboard
45 MiniMax-M3 7.58% ±2.8 none, mini-swe-agent SWE-agent Jun 2026 Jun 2026 Official leaderboard
46 Claude Code + DeepSeek V4 Pro 0813 6.67% ±2.5 max Anthropic Aug 2026 Aug 2026 Official leaderboard
47 Beam 1.0 6.36% ±1.7 none, mini-swe-agent SWE-agent Oct 2026 Oct 2026 Official leaderboard
48 Gemini 3.1 Pro 2.73% ±1.7 high, Antigravity CLI Google Feb 2026 Feb 2026 Official leaderboard
49 GPT-5.4 Mini 1.82% ±1.3 xhigh, Codex OpenAI Mar 2026 Mar 2026 Official leaderboard
50 Inkling-Small 0.91% ±0.9 none, mini-swe-agent SWE-agent Jul 2026 Jul 2026 Official leaderboard
51 Nemotron 3.5 Super VL 0.30% ±0.6 none, mini-swe-agent SWE-agent Oct 2026 Oct 2026 Official leaderboard
52 Inkling 0% none, mini-swe-agent SWE-agent Jul 2026 Jul 2026 Official leaderboard
#ModelScore ± 95% CISettingAgent byReleasedRun onSource
1 Copilot Fusion router 71.2% ±2.9 max, GitHub Copilot GitHub Oct 2026 Nov 2026 Official leaderboard
2 Claude Opus 5.5 65.8% ±3.1 max, Claude Code Anthropic Sep 2026 Sep 2026 Official leaderboard
3 Claude Fable 5.2 65.8% ±2.9 max, Claude Code Anthropic Nov 2026 Nov 2026 Official leaderboard
4 Gemini 4 Carbon 64.5% ±3.2 high, Antigravity CLI Google Oct 2026 Oct 2026 Official leaderboard
5 Claude Sonnet 5.5 63.9% ±3 max, Claude Code Anthropic Sep 2026 Sep 2026 Official leaderboard
6 GPT-6.2 Astra 62.1% ±2.3 max, Codex OpenAI Nov 2026 Nov 2026 Official leaderboard
7 GPT-6.2 Sol 61.5% ±2.7 max, Codex OpenAI Nov 2026 Nov 2026 Official leaderboard
8 GPT-6.1 Sol 60.9% ±3 max, Codex OpenAI Sep 2026 Sep 2026 Official leaderboard
9 GPT-6 Astra 60.3% ±2.8 max, Codex OpenAI Sep 2026 Sep 2026 Official leaderboard
10 Claude Fable 5.1 57.6% ±3.3 xhigh, Claude Code Anthropic Sep 2026 Sep 2026 Official leaderboard
11 Gemini 4 Hydrogen 56.4% ±3 high, Antigravity CLI Google Nov 2026 Nov 2026 Official leaderboard
12 Gemini 4 Argon 55.5% ±2.8 high, Antigravity CLI Google Sep 2026 Sep 2026 Official leaderboard
13 Claude Opus 5 53.3% ±3.1 xhigh, Claude Code Anthropic Jul 2026 Jul 2026 Official leaderboard
14 GPT-6.1 Terra 53.3% ±3.1 max, Codex OpenAI Oct 2026 Oct 2026 Official leaderboard
15 GPT-6 Sol 50.3% ±3.2 max, Codex OpenAI Sep 2026 Sep 2026 Official leaderboard
16 Muse Wonder 47% ±3.8 xhigh, Muse Code Meta Oct 2026 Oct 2026 Official leaderboard
17 Claude Fable 5 44.9% ±3.8 max, Claude Code Anthropic Jun 2026 Jun 2026 Official leaderboard
18 Claude Haiku 5.5 40% ±3.6 max, Claude Code Anthropic Oct 2026 Oct 2026 Official leaderboard
19 Grok 4.7 38.8% ±3.6 xhigh, Grok Build xAI Sep 2026 Sep 2026 Official leaderboard
20 GPT-5.6 Sol 38.5% ±3.8 max, Codex OpenAI Jul 2026 Jun 2026 Official leaderboard
21 Muse Ember 30.6% ±3.8 xhigh, Muse Code Meta Nov 2026 Nov 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 Ember-1 21.8% ±3.5 none, mini-swe-agent SWE-agent Sep 2026 Sep 2026 Official leaderboard
25 GPT-5.6 Terra 21.5% ±3.3 max, Codex OpenAI Jul 2026 Jun 2026 Official leaderboard
26 Grok 4.6 19.7% ±3.1 high, Grok Build xAI Aug 2026 Aug 2026 Official leaderboard
27 Gemini 3.8 Flash 18.2% ±3.4 high, mini-SWE-agent SWE-agent Sep 2026 Sep 2026 Official leaderboard
28 GPT-5.6 Luna 17.6% ±2.9 max, Codex OpenAI Jul 2026 Jun 2026 Official leaderboard
29 MiMo-V2.6 Flash 16.1% ±3.4 none, mini-swe-agent SWE-agent Sep 2026 Sep 2026 Official leaderboard
30 GPT-6 Luna 15.2% ±2.7 max, Codex OpenAI Sep 2026 Sep 2026 Official leaderboard
31 Muse Spark 1.3 14.8% ±3 xhigh, Muse Code Meta Sep 2026 Sep 2026 Official leaderboard
32 Inkling 2 Small 13% ±2.9 xhigh, mini-swe-agent SWE-agent Nov 2026 Nov 2026 Official leaderboard
33 Grok 4.5 12.4% ±2.6 high, Grok Build xAI Jul 2026 Jul 2026 Official leaderboard
34 Gemini 3.7 Flash 12.4% ±2.5 high, mini-SWE-agent SWE-agent Aug 2026 Aug 2026 Official leaderboard
35 Claude Sonnet 5 12.1% ±3 max, Claude Code Anthropic Jun 2026 Jun 2026 Official leaderboard
36 MiniMax-M3 7.58% ±2.8 none, mini-swe-agent SWE-agent Jun 2026 Jun 2026 Official leaderboard
37 Beam 1.0 6.36% ±1.7 none, mini-swe-agent SWE-agent Oct 2026 Oct 2026 Official leaderboard
38 Gemini 3.1 Pro 2.73% ±1.7 high, Antigravity CLI Google Feb 2026 Feb 2026 Official leaderboard
39 GPT-5.4 Mini 1.82% ±1.3 xhigh, Codex OpenAI Mar 2026 Mar 2026 Official leaderboard
40 Inkling-Small 0.91% ±0.9 none, mini-swe-agent SWE-agent Jul 2026 Jul 2026 Official leaderboard
41 Nemotron 3.5 Super VL 0.30% ±0.6 none, mini-swe-agent SWE-agent Oct 2026 Oct 2026 Official leaderboard
42 Inkling 0% none, mini-swe-agent SWE-agent Jul 2026 Jul 2026 Official leaderboard
#ModelScore ± 95% CISettingAgent byReleasedRun onSource
1 MiMo-V2.6 Pro 27% ±3.6 none, mini-swe-agent SWE-agent Sep 2026 Sep 2026 Official leaderboard
2 Ember-1 21.8% ±3.5 none, mini-swe-agent SWE-agent Sep 2026 Sep 2026 Official leaderboard
3 Gemini 3.8 Flash 18.2% ±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 Inkling 2 Small 13% ±2.9 xhigh, mini-swe-agent SWE-agent Nov 2026 Nov 2026 Official leaderboard
6 Gemini 3.7 Flash 12.4% ±2.5 high, mini-SWE-agent SWE-agent Aug 2026 Aug 2026 Official leaderboard
7 MiniMax-M3 7.58% ±2.8 none, mini-swe-agent SWE-agent Jun 2026 Jun 2026 Official leaderboard
8 Beam 1.0 6.36% ±1.7 none, mini-swe-agent SWE-agent Oct 2026 Oct 2026 Official leaderboard
9 Inkling-Small 0.91% ±0.9 none, mini-swe-agent SWE-agent Jul 2026 Jul 2026 Official leaderboard
10 Nemotron 3.5 Super VL 0.30% ±0.6 none, mini-swe-agent SWE-agent Oct 2026 Oct 2026 Official leaderboard
11 Inkling 0% none, mini-swe-agent SWE-agent Jul 2026 Jul 2026 Official leaderboard
#ModelScoreSettingDateSource
1 Copilot Fusion router 71.2% max, GitHub Copilot Oct 2026 Official leaderboard
2 Claude Opus 5.5 65.8% max, Claude Code Sep 2026 Official leaderboard
3 Claude Fable 5.2 65.8% max, Claude Code Nov 2026 Official leaderboard
4 Gemini 4 Neon 65.2% Nov 2026 Lab model card
5 Gemini 4 Carbon 64.5% high, Antigravity CLI Oct 2026 Official leaderboard
6 Claude Sonnet 5.5 63.9% max, Claude Code Sep 2026 Official leaderboard
7 GPT-6.2 Astra 62.1% max, Codex Nov 2026 Official leaderboard
8 GPT-6.2 Sol 61.5% max, Codex Nov 2026 Official leaderboard
9 GPT-6.1 Sol 60.9% max, Codex Sep 2026 Official leaderboard
10 GPT-6 Astra 60.3% max, Codex Sep 2026 Official leaderboard
11 Claude Fable 5.1 57.6% xhigh, Claude Code Sep 2026 Official leaderboard
12 Gemini 4 Hydrogen 57% Nov 2026 Lab model card
13 Gemini 4 Argon 55.5% high, Antigravity CLI Sep 2026 Official leaderboard
14 Claude Opus 5 53.3% xhigh, Claude Code Jul 2026 Official leaderboard
15 GPT-6.1 Terra 53.3% max, Codex Oct 2026 Official leaderboard
16 GPT-6 Sol 50.3% max, Codex Sep 2026 Official leaderboard
17 Muse Wonder 47% xhigh, Muse Code Oct 2026 Official leaderboard
18 Claude Fable 5 44.9% max, Claude Code Jun 2026 Official leaderboard
19 Claude Haiku 5.5 40% max, Claude Code Oct 2026 Official leaderboard
20 Grok 4.7 38.8% xhigh, Grok Build Sep 2026 Official leaderboard
21 GPT-5.6 Sol 38.5% max, Codex Jul 2026 Official leaderboard
22 Muse Ember 30.6% xhigh, Muse Code Nov 2026 Official leaderboard
23 MiMo-V2.6 Pro 27% none, mini-swe-agent Sep 2026 Official leaderboard
24 Claude Opus 4.8 23.6% max, Claude Code May 2026 Official leaderboard
25 Ember-1 21.8% none, mini-swe-agent Sep 2026 Official leaderboard
26 GPT-5.6 Terra 21.5% max, Codex Jul 2026 Official leaderboard
27 Grok 4.6 19.7% high, Grok Build Aug 2026 Official leaderboard
28 Gemini 3.8 Flash 18.2% high, mini-SWE-agent Sep 2026 Official leaderboard
29 GPT-5.6 Luna 17.6% max, Codex Jul 2026 Official leaderboard
30 MiMo-V2.6 Flash 16.1% none, mini-swe-agent Sep 2026 Official leaderboard
31 GPT-6 Luna 15.2% max, Codex Sep 2026 Official leaderboard
32 Muse Spark 1.3 14.8% xhigh, Muse Code Sep 2026 Official leaderboard
33 Inkling 2 Small 13% xhigh, mini-swe-agent Nov 2026 Official leaderboard
34 Grok 4.5 12.4% high, Grok Build Jul 2026 Official leaderboard
35 Gemini 3.7 Flash 12.4% high, mini-SWE-agent Aug 2026 Official leaderboard
36 Claude Sonnet 5 12.1% max, Claude Code Jun 2026 Official leaderboard
37 MiniMax-M3 7.58% none, mini-swe-agent Jun 2026 Official leaderboard
38 Beam 1.0 6.36% none, mini-swe-agent Oct 2026 Official leaderboard
39 Gemini 3.1 Pro 2.73% high, Antigravity CLI Feb 2026 Official leaderboard
40 GPT-5.4 Mini 1.82% xhigh, Codex Mar 2026 Official leaderboard
41 Inkling-Small 0.91% none, mini-swe-agent Jul 2026 Official leaderboard
42 Nemotron 3.5 Super VL 0.30% none, mini-swe-agent Oct 2026 Official leaderboard
43 Inkling 0% none, mini-swe-agent Jul 2026 Official leaderboard

Labs report scores for 2 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.

0% 20% 40% 60% 80% 1001,00010K Mean time per trial (s), log scale, lower is better Accuracy Copilot Fusion (max)Gemini 4 Carbon (high)GPT-6.2 Astra (max)GPT-6.2 Sol (max)Claude Code + Kimi K3.1 Pro (max)GPT-6.1 Terra (max)Claude Code + GLM-5.3-Flash (max) 0% 20% 40% 60% 80% 1001,00010K Mean time per trial (s), log scale, lower is better Accuracy Copilot Fusion (max)Gemini 4 Carbon (high)GPT-6.2 Astra (max)GPT-6.2 Sol (max)Claude Code + Kimi K3.1 Pro (max)GPT-6.1 Terra (max)Claude Code + GLM-5.3-Flash (max)
ModelSettingAccuracyMean time per trial
Copilot Fusion router max, GitHub Copilot 71.2% 4,234 s
Claude Opus 5.5 max, Claude Code 65.8% 4,790 s
Claude Fable 5.2 max, Claude Code 65.8% 7,333 s
Gemini 4 Carbon high, Antigravity CLI 64.6% 3,496 s
Claude Sonnet 5.5 max, Claude Code 63.9% 7,432 s
GPT-6.2 Astra max, Codex 62.1% 1,350 s
GPT-6.2 Sol max, Codex 61.5% 1,214 s
GPT-6.1 Sol max, Codex 60.9% 3,177 s
GPT-6 Astra max, Codex 60.3% 2,796 s
GPT-6 Astra high, Codex 60% 2,114 s
Claude Code + Kimi K3.1 Pro max, Claude Code 59.7% 123.2 s
GPT-6 Astra xhigh, Codex 59.7% 2,209 s
Claude Fable 5.1 xhigh, Claude Code 57.6% 3,202 s
Claude Fable 5.1 max, Claude Code 57.3% 3,894 s
Gemini 4 Hydrogen high, Antigravity CLI 56.4% 1,926 s
Gemini 4 Argon high, Antigravity CLI 55.5% 125.2 s
GPT-6 Astra medium, Codex 55.2% 1,886 s
Claude Fable 5.1 high, Claude Code 54.9% 3,018 s
Claude Fable 5.1 medium, Claude Code 53.9% 2,528 s
GPT-6.1 Terra max, Codex 53.3% 123.1 s
Claude Opus 5 xhigh, Claude Code 53.3% 4,515 s
Claude Opus 5 max, Claude Code 52.1% 4,793 s
GPT-6 Astra low, Codex 50.9% 1,684 s
GPT-6 Sol max, Codex 50.3% 2,662 s
Claude Opus 5 high, Claude Code 49.7% 3,822 s
Muse Wonder xhigh, Muse Code 47% 2,828 s
Claude Opus 5 medium, Claude Code 45.2% 3,293 s
Claude Fable 5 max, Claude Code 44.9% 4,203 s
Claude Fable 5.1 low, Claude Code 43.3% 2,291 s
Claude Code + GLM-5.3 max, Claude Code 41.2% 5,831 s
Claude Haiku 5.5 max, Claude Code 40% 140.5 s
Grok 4.7 xhigh, Grok Build 38.8% 5,701 s
Claude Code + DeepSeek V4.1 Flash 1017 max, Claude Code 38.5% 148.4 s
GPT-5.6 Sol max, Codex 38.5% 2,388 s
Claude Code + Tencent Hy4 max, Claude Code 37.9% 126.2 s
Claude Code + GLM-5.3-Flash max, Claude Code 37% 120.4 s
Claude Code + GLM-5.3-Flash none, Claude Code 35.5% 6,210 s
Claude Opus 5 low, Claude Code 34.9% 2,947 s
Muse Ember xhigh, Muse Code 30.6% 2,288 s
Claude Code + Mistral Large 4 max, Claude Code 27.6% 142.7 s
MiMo-V2.6 Pro none, mini-swe-agent 27% 168.2 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 23% 141.9 s
Ember-1 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 19.7% 2,352 s
Claude Code + Tencent Hy4 preview max, Claude Code 19.1% 6,967 s
Gemini 3.8 Flash high, mini-SWE-agent 18.2% 1,995 s
GPT-5.6 Luna max, Codex 17.6% 4,088 s
MiMo-V2.6 Flash none, mini-swe-agent 16.1% 160.8 s
GPT-6 Luna max, Codex 15.2% 2,284 s
Muse Spark 1.3 xhigh, Muse Code 14.9% 4,342 s
Inkling 2 Small xhigh, mini-swe-agent 13% 7,273 s
Gemini 3.7 Flash high, mini-SWE-agent 12.4% 1,689 s
Grok 4.5 high, Grok Build 12.4% 3,162 s
Claude Sonnet 5 max, Claude Code 12.1% 6,510 s
MiniMax-M3 none, mini-swe-agent 7.6% 204 s
Claude Code + DeepSeek V4 Pro 0813 max, Claude Code 6.7% 138.2 s
Beam 1.0 none, mini-swe-agent 6.4% 178.6 s
Gemini 3.1 Pro high, Antigravity CLI 2.7% 4,583 s
GPT-5.4 Mini xhigh, Codex 1.8% 141.5 s
Inkling-Small none, mini-swe-agent 0.9% 141.3 s
Nemotron 3.5 Super VL none, mini-swe-agent 0.3% 135.8 s
Inkling none, mini-swe-agent 0% 174.1 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.

0% 20% 40% 60% 80% 1001,00010K Mean time per trial (s), log scale, lower is better Accuracy Copilot Fusion (max)Gemini 4 Carbon (high)GPT-6.2 Astra (max)GPT-6.2 Sol (max)Gemini 4 Argon (high)GPT-6.1 Terra (max) 0% 20% 40% 60% 80% 1001,00010K Mean time per trial (s), log scale, lower is better Accuracy Copilot Fusion (max)Gemini 4 Carbon (high)GPT-6.2 Astra (max)GPT-6.2 Sol (max)Gemini 4 Argon (high)GPT-6.1 Terra (max)
ModelSettingAccuracyMean time per trial
Copilot Fusion router max, GitHub Copilot 71.2% 4,234 s
Claude Opus 5.5 max, Claude Code 65.8% 4,790 s
Claude Fable 5.2 max, Claude Code 65.8% 7,333 s
Gemini 4 Carbon high, Antigravity CLI 64.6% 3,496 s
Claude Sonnet 5.5 max, Claude Code 63.9% 7,432 s
GPT-6.2 Astra max, Codex 62.1% 1,350 s
GPT-6.2 Sol max, Codex 61.5% 1,214 s
GPT-6.1 Sol max, Codex 60.9% 3,177 s
GPT-6 Astra max, Codex 60.3% 2,796 s
GPT-6 Astra high, Codex 60% 2,114 s
GPT-6 Astra xhigh, Codex 59.7% 2,209 s
Claude Fable 5.1 xhigh, Claude Code 57.6% 3,202 s
Claude Fable 5.1 max, Claude Code 57.3% 3,894 s
Gemini 4 Hydrogen high, Antigravity CLI 56.4% 1,926 s
Gemini 4 Argon high, Antigravity CLI 55.5% 125.2 s
GPT-6 Astra medium, Codex 55.2% 1,886 s
Claude Fable 5.1 high, Claude Code 54.9% 3,018 s
Claude Fable 5.1 medium, Claude Code 53.9% 2,528 s
GPT-6.1 Terra max, Codex 53.3% 123.1 s
Claude Opus 5 xhigh, Claude Code 53.3% 4,515 s
Claude Opus 5 max, Claude Code 52.1% 4,793 s
GPT-6 Astra low, Codex 50.9% 1,684 s
GPT-6 Sol max, Codex 50.3% 2,662 s
Claude Opus 5 high, Claude Code 49.7% 3,822 s
Muse Wonder xhigh, Muse Code 47% 2,828 s
Claude Opus 5 medium, Claude Code 45.2% 3,293 s
Claude Fable 5 max, Claude Code 44.9% 4,203 s
Claude Fable 5.1 low, Claude Code 43.3% 2,291 s
Claude Haiku 5.5 max, Claude Code 40% 140.5 s
Grok 4.7 xhigh, Grok Build 38.8% 5,701 s
GPT-5.6 Sol max, Codex 38.5% 2,388 s
Claude Opus 5 low, Claude Code 34.9% 2,947 s
Muse Ember xhigh, Muse Code 30.6% 2,288 s
MiMo-V2.6 Pro none, mini-swe-agent 27% 168.2 s
Claude Opus 4.8 max, Claude Code 23.6% 5,163 s
Ember-1 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 19.7% 2,352 s
Gemini 3.8 Flash high, mini-SWE-agent 18.2% 1,995 s
GPT-5.6 Luna max, Codex 17.6% 4,088 s
MiMo-V2.6 Flash none, mini-swe-agent 16.1% 160.8 s
GPT-6 Luna max, Codex 15.2% 2,284 s
Muse Spark 1.3 xhigh, Muse Code 14.9% 4,342 s
Inkling 2 Small xhigh, mini-swe-agent 13% 7,273 s
Gemini 3.7 Flash high, mini-SWE-agent 12.4% 1,689 s
Grok 4.5 high, Grok Build 12.4% 3,162 s
Claude Sonnet 5 max, Claude Code 12.1% 6,510 s
MiniMax-M3 none, mini-swe-agent 7.6% 204 s
Beam 1.0 none, mini-swe-agent 6.4% 178.6 s
Gemini 3.1 Pro high, Antigravity CLI 2.7% 4,583 s
GPT-5.4 Mini xhigh, Codex 1.8% 141.5 s
Inkling-Small none, mini-swe-agent 0.9% 141.3 s
Nemotron 3.5 Super VL none, mini-swe-agent 0.3% 135.8 s
Inkling none, mini-swe-agent 0% 174.1 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.

0% 10% 20% 30% 1001,00010K Mean time per trial (s), log scale, lower is better Accuracy MiMo-V2.6 Pro (none)MiMo-V2.6 Flash (none)Inkling-Small (none)Nemotron 3.5 Super VL (none) 0% 10% 20% 30% 1001,00010K Mean time per trial (s), log scale, lower is better Accuracy MiMo-V2.6 Pro (none)MiMo-V2.6 Flash (none)Inkling-Small (none)Nemotron 3.5 Super VL (none)
ModelSettingAccuracyMean time per trial
MiMo-V2.6 Pro none, mini-swe-agent 27% 168.2 s
Ember-1 none, mini-swe-agent 21.8% 4,960 s
Gemini 3.8 Flash high, mini-SWE-agent 18.2% 1,995 s
MiMo-V2.6 Flash none, mini-swe-agent 16.1% 160.8 s
Inkling 2 Small xhigh, mini-swe-agent 13% 7,273 s
Gemini 3.7 Flash high, mini-SWE-agent 12.4% 1,689 s
MiniMax-M3 none, mini-swe-agent 7.6% 204 s
Beam 1.0 none, mini-swe-agent 6.4% 178.6 s
Inkling-Small none, mini-swe-agent 0.9% 141.3 s
Nemotron 3.5 Super VL none, mini-swe-agent 0.3% 135.8 s
Inkling none, mini-swe-agent 0% 174.1 s

The best score, 71.2%, costs $6.02 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.

Thinking Machines OpenAI GitHub Google DeepMind Agents other companies built, in a pale shade of the model’s lab Cost frontier One model at each effort level
0% 20% 40% 60% 80% 100% $0.10 $1.00 $10 $100 Cost per task, log scale Copilot Fusion, max Gemini 4 Carbon, high GPT-6.2 Sol, max Claude Code + DeepSeek V4.1 Flash 1017, max GPT-6 Luna, max Inkling-Small, none 0% 20% 40% 60% 80% 100% $0.10 $1.00 $10 $100 Cost per task, log scale Copilot Fusion, max Gemini 4 Carbon, high

Source: Official Terminal-Bench 4.1 leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
Copilot Fusion router max GitHub Copilot 71.2% $6.02 243,149
Claude Opus 5.5 max Claude Code 65.8% $14 269,135
Claude Fable 5.2 max Claude Code 65.8% $50 491,352
Gemini 4 Carbon high Antigravity CLI 64.5% $4.12 166,082
Claude Sonnet 5.5 max Claude Code 63.9% $22 565,388
GPT-6.2 Astra max Codex 62.1% $4.27 49,894
GPT-6.2 Sol max Codex 61.5% $1.06 48,561
GPT-6.1 Sol max Codex 60.9% $1.92 94,892
GPT-6 Astra max Codex 60.3% $9.90 72,694
GPT-6 Astra high Codex 60% $6.88 41,527
GPT-6 Astra xhigh Codex 59.7% $7.12 45,304
Claude Code + Kimi K3.1 Pro max Claude Code 59.7% $3.29 80,956
Claude Fable 5.1 xhigh Claude Code 57.6% $15 152,809
Claude Fable 5.1 max Claude Code 57.3% $19 191,277
Gemini 4 Hydrogen high Antigravity CLI 56.4% $2.38 119,482
Gemini 4 Argon high Antigravity CLI 55.5% $3.36 162,988
GPT-6 Astra medium Codex 55.1% $5.80 32,638
Claude Fable 5.1 high Claude Code 54.9% $12 113,421
Claude Fable 5.1 medium Claude Code 53.9% $8.59 78,763
Claude Opus 5 xhigh Claude Code 53.3% $18 179,281
GPT-6.1 Terra max Codex 53.3% $2.65 100,138
Claude Opus 5 max Claude Code 52.1% $18 200,037
GPT-6 Astra low Codex 50.9% $4.72 24,207
GPT-6 Sol max Codex 50.3% $4.40 92,642
Claude Opus 5 high Claude Code 49.7% $14 144,242
Muse Wonder xhigh Muse Code 47% $7.43 129,324
Claude Opus 5 medium Claude Code 45.1% $9.67 101,450
Claude Fable 5 max Claude Code 44.9% $22 177,636
Claude Fable 5.1 low Claude Code 43.3% $7.15 60,409
Claude Code + GLM-5.3 max Claude Code 41.2% $8.27 208,061
Claude Haiku 5.5 max Claude Code 40% $2.89 386,483
Grok 4.7 xhigh Grok Build 38.8% $11 69,627
GPT-5.6 Sol max Codex 38.5% $7.70 71,065
Claude Code + DeepSeek V4.1 Flash 1017 max Claude Code 38.5% $0.56 497,265
Claude Code + Tencent Hy4 max Claude Code 37.9% $1.05 368,811
Claude Code + GLM-5.3-Flash max Claude Code 37% $1.14 459,702
Claude Code + GLM-5.3-Flash none Claude Code 35.5% $0.36 135,014
Claude Opus 5 low Claude Code 34.9% $7.25 72,229
Muse Ember xhigh Muse Code 30.6% $0.48 165,351
Claude Code + Mistral Large 4 max Claude Code 27.6% $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 23% $5.82 195,427
Ember-1 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 19.7% $11 98,843
Claude Code + Tencent Hy4 preview max Claude Code 19.1% $1.99 309,296
Gemini 3.8 Flash high mini-SWE-agent 18.2% $5.54 206,232
GPT-5.6 Luna max Codex 17.6% $1.05 185,705
MiMo-V2.6 Flash none mini-swe-agent 16.1% $0.59 200,090
GPT-6 Luna max Codex 15.2% $0.22 137,851
Muse Spark 1.3 xhigh Muse Code 14.8% 265,112
Inkling 2 Small xhigh mini-swe-agent 13% $2.92 309,788
Grok 4.5 high Grok Build 12.4% $6.35 98,149
Gemini 3.7 Flash high mini-SWE-agent 12.4% $3.82 157,982
Claude Sonnet 5 max Claude Code 12.1% $29 353,330
MiniMax-M3 none mini-swe-agent 7.58% $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% $0.67 64,523
Gemini 3.1 Pro high Antigravity CLI 2.73% $11 87,678
GPT-5.4 Mini xhigh Codex 1.82% $2.04 169,597
Inkling-Small none mini-swe-agent 0.91% $0.15 20,104
Nemotron 3.5 Super VL none mini-swe-agent 0.30% $0.51 159,709
Inkling none mini-swe-agent 0% $3.06 39,308

The best score, 71.2%, costs $6.02 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.

Thinking Machines OpenAI GitHub Google DeepMind Meta Cost frontier One model at each effort level
0% 20% 40% 60% 80% 100% $0.10 $1.00 $10 $100 Cost per task, log scale Copilot Fusion, max Gemini 4 Carbon, high GPT-6.2 Sol, max Muse Ember, xhigh GPT-6 Luna, max Inkling-Small, none 0% 20% 40% 60% 80% 100% $0.10 $1.00 $10 $100 Cost per task, log scale Copilot Fusion, max Gemini 4 Carbon, high

Source: Official Terminal-Bench 4.1 leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
Copilot Fusion router max GitHub Copilot 71.2% $6.02 243,149
Claude Opus 5.5 max Claude Code 65.8% $14 269,135
Claude Fable 5.2 max Claude Code 65.8% $50 491,352
Gemini 4 Carbon high Antigravity CLI 64.5% $4.12 166,082
Claude Sonnet 5.5 max Claude Code 63.9% $22 565,388
GPT-6.2 Astra max Codex 62.1% $4.27 49,894
GPT-6.2 Sol max Codex 61.5% $1.06 48,561
GPT-6.1 Sol max Codex 60.9% $1.92 94,892
GPT-6 Astra max Codex 60.3% $9.90 72,694
GPT-6 Astra high Codex 60% $6.88 41,527
GPT-6 Astra xhigh Codex 59.7% $7.12 45,304
Claude Fable 5.1 xhigh Claude Code 57.6% $15 152,809
Claude Fable 5.1 max Claude Code 57.3% $19 191,277
Gemini 4 Hydrogen high Antigravity CLI 56.4% $2.38 119,482
Gemini 4 Argon high Antigravity CLI 55.5% $3.36 162,988
GPT-6 Astra medium Codex 55.1% $5.80 32,638
Claude Fable 5.1 high Claude Code 54.9% $12 113,421
Claude Fable 5.1 medium Claude Code 53.9% $8.59 78,763
Claude Opus 5 xhigh Claude Code 53.3% $18 179,281
GPT-6.1 Terra max Codex 53.3% $2.65 100,138
Claude Opus 5 max Claude Code 52.1% $18 200,037
GPT-6 Astra low Codex 50.9% $4.72 24,207
GPT-6 Sol max Codex 50.3% $4.40 92,642
Claude Opus 5 high Claude Code 49.7% $14 144,242
Muse Wonder xhigh Muse Code 47% $7.43 129,324
Claude Opus 5 medium Claude Code 45.1% $9.67 101,450
Claude Fable 5 max Claude Code 44.9% $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 38.8% $11 69,627
GPT-5.6 Sol max Codex 38.5% $7.70 71,065
Claude Opus 5 low Claude Code 34.9% $7.25 72,229
Muse Ember xhigh Muse Code 30.6% $0.48 165,351
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
Ember-1 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 19.7% $11 98,843
Gemini 3.8 Flash high mini-SWE-agent 18.2% $5.54 206,232
GPT-5.6 Luna max Codex 17.6% $1.05 185,705
MiMo-V2.6 Flash none mini-swe-agent 16.1% $0.59 200,090
GPT-6 Luna max Codex 15.2% $0.22 137,851
Muse Spark 1.3 xhigh Muse Code 14.8% 265,112
Inkling 2 Small xhigh mini-swe-agent 13% $2.92 309,788
Grok 4.5 high Grok Build 12.4% $6.35 98,149
Gemini 3.7 Flash high mini-SWE-agent 12.4% $3.82 157,982
Claude Sonnet 5 max Claude Code 12.1% $29 353,330
MiniMax-M3 none mini-swe-agent 7.58% $3.48 234,421
Beam 1.0 none mini-swe-agent 6.36% $0.67 64,523
Gemini 3.1 Pro high Antigravity CLI 2.73% $11 87,678
GPT-5.4 Mini xhigh Codex 1.82% $2.04 169,597
Inkling-Small none mini-swe-agent 0.91% $0.15 20,104
Nemotron 3.5 Super VL none mini-swe-agent 0.30% $0.51 159,709
Inkling 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.

Thinking Machines Xiaomi Corp Cost frontier One model at each effort level
0% 10% 20% 30% $0.10 $1.00 $10 $100 Cost per task, log scale MiMo-V2.6 Pro, none MiMo-V2.6 Flash, none Inkling-Small, none 0% 10% 20% 30% $0.10 $1.00 $10 $100 Cost per task, log scale MiMo-V2.6 Pro, none MiMo-V2.6 Flash, none

Source: Official Terminal-Bench 4.1 leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
MiMo-V2.6 Pro none mini-swe-agent 27% $0.86 245,849
Ember-1 none mini-swe-agent 21.8% $14 187,695
Gemini 3.8 Flash high mini-SWE-agent 18.2% $5.54 206,232
MiMo-V2.6 Flash none mini-swe-agent 16.1% $0.59 200,090
Inkling 2 Small xhigh mini-swe-agent 13% $2.92 309,788
Gemini 3.7 Flash high mini-SWE-agent 12.4% $3.82 157,982
MiniMax-M3 none mini-swe-agent 7.58% $3.48 234,421
Beam 1.0 none mini-swe-agent 6.36% $0.67 64,523
Inkling-Small none mini-swe-agent 0.91% $0.15 20,104
Nemotron 3.5 Super VL none mini-swe-agent 0.30% $0.51 159,709
Inkling none mini-swe-agent 0% $3.06 39,308

Number one over time Number one over time

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.

GitHub Google DeepMind
Own leaderboard 1 leader
Copilot Fusion 71.2%
Lab claims 2 leaders

Sources: Official Terminal-Bench 4.1 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.

Plot with other benchmarks
On the benchmark’s own leaderboard Reported by the lab in its model card Best so far
0% 20% 40% 60% 80% 100% 2026 2027 Near the ceiling (85%) Copilot Fusion Claude Opus 5.5 GPT-6 Astra Claude Opus 5 Claude Fable 5 Claude Opus 4.8 Gemini 3.1 Pro 0% 20% 40% 60% 80% 100% 2026 2027 Near the ceiling (85%) Copilot Fusion GPT-6 Astra

Sources: Official Terminal-Bench 4.1 leaderboard and labs’ model cards

On the benchmark’s own leaderboard Reported by the lab in its model card Best so far
0% 20% 40% 60% 80% 100% 2026 2027 Near the ceiling (85%) Gemini 4 Neon Gemini 4 Hydrogen MiMo-V2.6 Pro Gemini 3.8 Flash Gemini 3.7 Flash MiniMax-M3 0% 20% 40% 60% 80% 100% 2026 2027 Near the ceiling (85%) Gemini 4 Neon Gemini 4 Hydrogen

Sources: Official Terminal-Bench 4.1 leaderboard and labs’ model cards

One lab 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.

Google DeepMind
DateLaunch postScoreAs the post writes it
Nov 18, 2026 Gemini 4 Neon 65.2 Terminal-bench 4.1 (Cheating adjusted accuracy)
Nov 12, 2026 Gemini 4 Hydrogen 57 Terminal-Bench 4.1 (Cheating-adjusted)

One system card reports it

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.

DateDocumentScoreAs the document writes itSection
Nov 18, 2026 Gemini 4 Neon model card 65.2 Terminal-bench 4.1 (Cheating adjusted accuracy) (results table, p.4) Capabilities

One lab claim next to the leaderboard

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. Every benchmark.

Model Lab says Board says Gap
Gemini 4 Hydrogen 57% Terminal-Bench 4.1 (Cheating-adjusted) 56.4% Leaderboard, high, Antigravity CLI +0.6 pts

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.

Google DeepMind Anthropic OpenAI GitHub
Terminal-Bench 4.1 20 leaders
Copilot Fusion 71.2%
Terminal-Bench Replaced by 2.0, Nov 2025
GPT-5 49.6%
Terminal-Bench 2.0 Replaced by 2.1, May 2026
GPT-5.5 82.3%
Terminal-Bench 2.1 Passed 85% in Sep 2026, by GPT-6 Astra
GPT-6 Astra 87.4%
Terminal-Bench 3.0 Replaced by 4.0, Aug 2026
Copilot Fusion 71.2%

Sources: Official leaderboards and boards copied by Epoch AI (CC BY 4.0)

More in Terminal agents

All 35 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

All 12 checks pass. 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 (52 entries), launch posts (2 scores) and system cards (1 score).
  • Pass Models scored 43 models we track, plus 10 other entries on its leaderboard.
  • Pass Newest score The newest is from November 2026, for Gemini 4 Neon.
  • Pass Frontier models 10 of the top 10 have a score, led by GPT-6.2 Astra (#1).
  • Pass Headroom The best is 71.2%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on tbench.ai: 65 rows for models we track at the last read.
  • Pass Last read November 18th, 2026.
  • Pass Read worked The last read worked.
Consistency 2 pass
  • Pass Lab claims The one pair agrees within 10 points.
  • Pass Known issues No published audit found problems.

How we check