Benchmark Almanac

Terminal-Bench 3.0

Claude Opus 5 42.7% leads since July 2026
Claude Opus 5 43.3% leads since July 2026
In use

Agents complete 74 tasks across 7 domains in sandboxed terminal environments. Verifier scripts grade each trial as pass or fail.

Released first as FrontierBench v0.1, the name Anthropic's Claude Opus 5 card uses. Terminal-Bench 4.0 succeeded it in August 2026.

Made by
Laude Institute and Harbor
Released
July 2026
Kind
Terminal tasks
Level
Expert
Scored
Checked automatically
Answers
Agent task
Tasks
All public
Strongest model tested
Claude Opus 5 #10 on the capability index
Last in a launch post
September 2026
Last model added
September 2026
Scores refreshed
November 12th, 2026
12
Entries on its own leaderboard, 11 models we track
6
Launch posts list it, from 6 labs
4
System cards report it, from 4 labs

Claude Opus 5 leads with 42.7% among models released by August 2026

Best score per entry from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders.

Claude Opus 5 leads with 43.3%, 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.

The newest model with a score here came out in August 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 42.7 Claude Opus 5
  2. 34.6 GPT-5.6 Sol
  3. 34.0 Claude Fable 5
  4. 32.4 GLM-5.3
  5. 26.5 Grok 4.6
  6. 21.1 Claude Opus 4.8
  7. 20.8 GPT-5.6 Terra
  8. 18.6 SWE-1.7 Lightning
  9. 15.7 Grok 4.5
  10. 14.6 Claude Sonnet 5
  11. 14.3 GPT-5.6 Luna
  12. 4.59 GLM-5.2
  1. 1 Claude Opus 5 max 42.7%
  2. 2 GPT-5.6 Sol max 34.6%
  3. 3 Claude Fable 5 max 34%
  4. 4 GLM-5.3 max 32.4%
  5. 5 Grok 4.6 high 26.5%
  6. 6 Claude Opus 4.8 max 21.1%
  7. 7 GPT-5.6 Terra max 20.8%
  8. 8 SWE-1.7 Lightning 18.6%
  9. 9 Grok 4.5 xhigh 15.7%
  10. 10 Claude Sonnet 5 max 14.6%
  11. 11 GPT-5.6 Luna max 14.3%
  12. 12 GLM-5.2 max 4.59%

Source: Official Terminal-Bench 3.0 leaderboard

Sources: Labs’ model cards and official Terminal-Bench 3.0 leaderboard

#EntryScoreSettingDateSource
1 Claude Opus 5 42.7% max, mini-SWE-agent Jul 2026 Official leaderboard
2 GPT-5.6 Sol 34.6% max, Codex Jul 2026 Official leaderboard
3 Claude Fable 5 34% max, Claude Code Jun 2026 Official leaderboard
4 GLM-5.3 32.4% max, Claude Code Aug 2026 Official leaderboard
5 Grok 4.6 26.5% high, Grok Build Aug 2026 Official leaderboard
6 Claude Opus 4.8 21.1% max, Claude Code May 2026 Official leaderboard
7 GPT-5.6 Terra 20.8% max, Codex Jul 2026 Official leaderboard
8 SWE-1.7 Lightning 18.6% Devin Aug 2026 Official leaderboard
9 Grok 4.5 15.7% xhigh, Cursor CLI Jul 2026 Official leaderboard
10 Claude Sonnet 5 14.6% max, Claude Code Jun 2026 Official leaderboard
11 GPT-5.6 Luna 14.3% max, Codex Jul 2026 Official leaderboard
12 GLM-5.2 4.59% max, Claude Code Jun 2026 Official leaderboard
#ModelScoreSettingDateSource
1 Claude Opus 5 43.3% Jul 2026 Lab model card
2 GPT-5.6 Sol 34.6% max, Codex Jul 2026 Official leaderboard
3 Claude Fable 5 34% max, Claude Code Jun 2026 Official leaderboard
4 GLM-5.3 32.4% max, Claude Code Aug 2026 Official leaderboard
5 DeepSeek V4.1 Flash 30% Sep 2026 Lab model card
6 Qwen3.8 Max (0902) 29% Sep 2026 Lab model card
7 Grok 4.6 26.5% high, Grok Build Aug 2026 Official leaderboard
8 Claude Opus 4.8 21.1% max, Claude Code May 2026 Official leaderboard
9 GPT-5.6 Terra 20.8% max, Codex Jul 2026 Official leaderboard
10 Grok 4.5 15.7% xhigh, Cursor CLI Jul 2026 Official leaderboard
11 Gemini 3.7 Flash 14.9% Aug 2026 Lab model card
12 Claude Sonnet 5 14.6% max, Claude Code Jun 2026 Official leaderboard
13 GPT-5.6 Luna 14.3% max, Codex Jul 2026 Official leaderboard
14 GLM-5.2 4.59% max, Claude Code Jun 2026 Official leaderboard

Labs report scores for 6 models in their cards. Switch the scores above to rank them together.

3 models have held number one on the official leaderboard since its release in July 2026 3 models have held number one with claims included since its release in July 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.

Anthropic OpenAI
Own leaderboard Replaced by 4.0, Aug 2026
Claude Opus 5 42.7%
Lab claims Replaced by 4.0, Sep 2026
Claude Opus 5 43.3%

Sources: Official Terminal-Bench 3.0 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.

On the benchmark’s own leaderboard Reported by the lab in its model card Best so far
0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Claude Opus 5 GPT-5.6 Sol Claude Opus 4.8 0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Claude Opus 5 GPT-5.6 Sol

Sources: Official Terminal-Bench 3.0 leaderboard and labs’ model cards

6 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.

Anthropic
xAI
Google DeepMind
Z.ai
Qwen
DeepSeek
DateLaunch postScoreAs the post writes it
Sep 10, 2026 DeepSeek V4.1 Flash 30 Terminal-Bench 3.0 (Pass@1)
Sep 2, 2026 Qwen3.8 Max (0902) 29 Agentic terminal coding, TerminalBench 3.0
Aug 14, 2026 GLM-5.3 28.3 Terminal Bench 3.0
Aug 13, 2026 Gemini 3.7 Flash 14.9 Terminal-bench 3.0
Aug 12, 2026 Grok 4.6 26 Terminal-Bench v3.0
Jul 24, 2026 Claude Opus 5 43.3 Agentic terminal coding Frontier-Bench v0.1

4 system cards report it, from 4 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.

DateDocumentScoreAs the document writes itSection
Sep 10, 2026 DeepSeek V4.1 Flash technical report 30 Terminal-Bench 3.0 (Pass@1) (Table 3) Capabilities
Aug 13, 2026 Gemini 3.7 Flash model card 14.9 Terminal-bench 3.0 (results table, p.5) Capabilities
Aug 12, 2026 Grok 4.6 model card 26 Terminal-Bench 3.0, task success rate, high, Grok Build harness, run by Harbor (2.6) Capabilities
Jul 24, 2026 Claude Opus 5 system card 43.3 FrontierBench v0.1, Harbor's evaluation (Table 8.1.A). Anthropic's own mini-SWE-agent run 44.4% mean reward at xhigh, 43% at max (8.5) Capabilities

The lab's number comes out ahead in 1 of 3 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. Every benchmark.

Model Lab says Board says Gap
GLM-5.3 28.3% Terminal Bench 3.0 32.4% Leaderboard, max, Claude Code −4.1 pts
Claude Opus 5 43.3% Agentic terminal coding Frontier-Bench v0.1 42.7% Leaderboard, max, mini-SWE-agent +0.6 pts
Grok 4.6 26% Terminal-Bench v3.0 26.5% Leaderboard, high, Grok Build −0.5 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
Terminal-Bench 4.1 20 leaders
Claude Opus 5.5 65.8%
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 84.7%
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
Claude Opus 5 42.7%
Terminal-Bench 4.0 4 leaders
Claude Opus 5.5 64.8%
Terminal-Bench 4.1 1 leader
Claude Opus 5.5 65.8%

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

Replaces Terminal-Bench 2.1 Replaced by Terminal-Bench 4.0

More in Terminal agents

All 19 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 67.3%
  • 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%
  • 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%
  • CompileBench Not in model cards Agents build real open-source projects through dependency problems, legacy toolchains and complex build systems, for example compiling 22-year-old code. Claude Opus 4.1 100%