Benchmark Almanac

Terminal-Bench-Science

GPT-6 Astra 68.1% leads since September 2026
Claude Fable 5.2 74.6% leads since November 2026
In use

70 scientific research-workflow tasks across five science areas, run in Harbor containers. Hidden tests give the resolution rate.

70 tasks kept from 920 proposals. v0.1. V0.2 in progress. Citation is a Zenodo DOI, no paper.

Released
August 2026
Kind
Research science
Level
Expert
Scored
Checked automatically
Answers
Agent task
Tasks
All public
Strongest model tested
Claude Fable 5.2 #1 on the capability index
Last in a launch post
November 2026
Last model added
November 2026
Scores refreshed
November 12th, 2026
17
Models scored on its own leaderboard
11
Launch posts list it, from 6 labs
6
System cards report it, from 2 labs

GPT-6 Astra leads with 68.1% among models released by September 2026

Best score per model from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best. Every run is in the next chart.

Claude Fable 5.2 leads with 74.6%, 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.

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

17 models. Scroll sideways for the rest.

  1. 68.1 GPT-6 Astra
  2. 63.3 Claude Opus 5.5
  3. 40.0 Claude Fable 5.1
  4. 30.0 Claude Opus 5
  5. 22.4 GPT-5.6 Sol
  6. 21.4 Claude Fable 5
  7. 15.7 DeepSeek V4.1 Flash
  8. 14.3 Grok 4.7
  9. 12.4 Gemini 3.8 Flash
  10. 10.5 Claude Opus 4.8
  11. 8.57 GPT-5.6 Terra
  12. 8.10 GLM-5.3
  13. 7.14 Kimi K3
  14. 7.14 Grok 4.6
  15. 5.71 Gemini 3.7 Flash
  16. 3.81 DeepSeek-V4-Pro
  17. 3.33 GPT-5.6 Luna
  1. 1 GPT-6 Astra max 68.1%
  2. 2 Claude Opus 5.5 max 63.3%
  3. 3 Claude Fable 5.1 max 40%
  4. 4 Claude Opus 5 max 30%
  5. 5 GPT-5.6 Sol max 22.4%
  6. 6 Claude Fable 5 max 21.4%
  7. 7 DeepSeek V4.1 Flash max 15.7%
  8. 8 Grok 4.7 xhigh 14.3%
  9. 9 Gemini 3.8 Flash high 12.4%
  10. 10 Claude Opus 4.8 max 10.5%
  11. 11 GPT-5.6 Terra max 8.57%
  12. 12 GLM-5.3 max 8.10%
  13. 13 Kimi K3 max 7.14%
  14. 14 Grok 4.6 xhigh 7.14%
  15. 15 Gemini 3.7 Flash high 5.71%
  16. 16 DeepSeek-V4-Pro max 3.81%
  17. 17 GPT-5.6 Luna max 3.33%

Source: Official Terminal-Bench-Science leaderboard

26 models. Scroll sideways for the rest.

  1. 74.6 Claude Fable 5.2
  2. 68.1 GPT-6 Astra
  3. 64.8 Gemini 4 Carbon
  4. 63.3 Claude Opus 5.5
  5. 59.9 Claude Sonnet 5.5
  6. 57.6 Gemini 4 Argon
  7. 57.0 GPT-6.1 Sol
  8. 52.6 Claude Fable 5.1
  9. 38.1 Kimi K3.1 Pro
  10. 30.0 Claude Opus 5
  11. 22.4 GPT-5.6 Sol
  12. 21.4 Claude Fable 5
  13. 20.6 Claude Haiku 5.5
  14. 19.8 Tencent Hy4
  15. 15.7 DeepSeek V4.1 Flash
  16. 14.3 Grok 4.7
  17. 12.4 Gemini 3.8 Flash
  18. 10.5 Claude Opus 4.8
  19. 8.57 GPT-5.6 Terra
  20. 8.10 GLM-5.3
  21. 7.14 Kimi K3
  22. 7.14 Grok 4.6
  23. 5.71 Gemini 3.7 Flash
  24. 5.70 Inkling 2 Small
  25. 3.81 DeepSeek-V4-Pro
  26. 3.33 GPT-5.6 Luna
  1. 1 Claude Fable 5.2 74.6%
  2. 2 GPT-6 Astra max 68.1%
  3. 3 Gemini 4 Carbon 64.8%
  4. 4 Claude Opus 5.5 max 63.3%
  5. 5 Claude Sonnet 5.5 59.9%
  6. 6 Gemini 4 Argon 57.6%
  7. 7 GPT-6.1 Sol 57%
  8. 8 Claude Fable 5.1 52.6%
  9. 9 Kimi K3.1 Pro 38.1%
  10. 10 Claude Opus 5 max 30%
  11. 11 GPT-5.6 Sol max 22.4%
  12. 12 Claude Fable 5 max 21.4%
  13. 13 Claude Haiku 5.5 20.6%
  14. 14 Tencent Hy4 19.8%
  15. 15 DeepSeek V4.1 Flash max 15.7%
  16. 16 Grok 4.7 xhigh 14.3%
  17. 17 Gemini 3.8 Flash high 12.4%
  18. 18 Claude Opus 4.8 max 10.5%
  19. 19 GPT-5.6 Terra max 8.57%
  20. 20 GLM-5.3 max 8.10%
  21. 21 Kimi K3 max 7.14%
  22. 22 Grok 4.6 xhigh 7.14%
  23. 23 Gemini 3.7 Flash high 5.71%
  24. 24 Inkling 2 Small 5.70%
  25. 25 DeepSeek-V4-Pro max 3.81%
  26. 26 GPT-5.6 Luna max 3.33%

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

#ModelScoreSettingDateSource
1 GPT-6 Astra 68.1% max, Codex Sep 2026 Official leaderboard
2 Claude Opus 5.5 63.3% max, Claude Code Sep 2026 Official leaderboard
3 Claude Fable 5.1 40% max, Claude Code Sep 2026 Official leaderboard
4 Claude Opus 5 30% max, Claude Code Jul 2026 Official leaderboard
5 GPT-5.6 Sol 22.4% max, Codex Jul 2026 Official leaderboard
6 Claude Fable 5 21.4% max, Claude Code Jun 2026 Official leaderboard
7 DeepSeek V4.1 Flash 15.7% max, Codex Sep 2026 Official leaderboard
8 Grok 4.7 14.3% xhigh, Grok Build Sep 2026 Official leaderboard
9 Gemini 3.8 Flash 12.4% high, mini-SWE-agent Sep 2026 Official leaderboard
10 Claude Opus 4.8 10.5% max, Claude Code May 2026 Official leaderboard
11 GPT-5.6 Terra 8.57% max, Codex Jul 2026 Official leaderboard
12 GLM-5.3 8.10% max, Claude Code Aug 2026 Official leaderboard
13 Kimi K3 7.14% max, Claude Code Jul 2026 Official leaderboard
14 Grok 4.6 7.14% xhigh, Grok Build Aug 2026 Official leaderboard
15 Gemini 3.7 Flash 5.71% high, mini-SWE-agent Aug 2026 Official leaderboard
16 DeepSeek-V4-Pro 3.81% max, Codex Apr 2026 Official leaderboard
17 GPT-5.6 Luna 3.33% max, Codex Jul 2026 Official leaderboard
#ModelScoreSettingDateSource
1 Claude Fable 5.2 74.6% Nov 2026 Lab model card
2 GPT-6 Astra 68.1% max, Codex Sep 2026 Official leaderboard
3 Gemini 4 Carbon 64.8% Oct 2026 Lab model card
4 Claude Opus 5.5 63.3% max, Claude Code Sep 2026 Official leaderboard
5 Claude Sonnet 5.5 59.9% Sep 2026 Lab model card
6 Gemini 4 Argon 57.6% Oct 2026 Lab model card
7 GPT-6.1 Sol 57% Sep 2026 Lab model card
8 Claude Fable 5.1 52.6% Sep 2026 Lab model card
9 Kimi K3.1 Pro 38.1% Oct 2026 Lab model card
10 Claude Opus 5 30% max, Claude Code Jul 2026 Official leaderboard
11 GPT-5.6 Sol 22.4% max, Codex Jul 2026 Official leaderboard
12 Claude Fable 5 21.4% max, Claude Code Jun 2026 Official leaderboard
13 Claude Haiku 5.5 20.6% Oct 2026 Lab model card
14 Tencent Hy4 19.8% Nov 2026 Lab model card
15 DeepSeek V4.1 Flash 15.7% max, Codex Sep 2026 Official leaderboard
16 Grok 4.7 14.3% xhigh, Grok Build Sep 2026 Official leaderboard
17 Gemini 3.8 Flash 12.4% high, mini-SWE-agent Sep 2026 Official leaderboard
18 Claude Opus 4.8 10.5% max, Claude Code May 2026 Official leaderboard
19 GPT-5.6 Terra 8.57% max, Codex Jul 2026 Official leaderboard
20 GLM-5.3 8.10% max, Claude Code Aug 2026 Official leaderboard
21 Kimi K3 7.14% max, Claude Code Jul 2026 Official leaderboard
22 Grok 4.6 7.14% xhigh, Grok Build Aug 2026 Official leaderboard
23 Gemini 3.7 Flash 5.71% high, mini-SWE-agent Aug 2026 Official leaderboard
24 Inkling 2 Small 5.70% Nov 2026 Lab model card
25 DeepSeek-V4-Pro 3.81% max, Codex Apr 2026 Official leaderboard
26 GPT-5.6 Luna 3.33% max, Codex Jul 2026 Official leaderboard

Labs report scores for 12 models in their cards. Switch the scores above to rank them together.

The best score, 68.1%, costs $24 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.

OpenAI DeepSeek Anthropic Cost frontier One model at each effort level
0% 20% 40% 60% 80% $1.00 $2.00 $5.00 $10 $20 $50 $100 Cost per task, log scale GPT-6 Astra, max Claude Opus 5.5, max GPT-5.6 Sol, max DeepSeek V4.1 Flash, max GPT-5.6 Luna, max 0% 20% 40% 60% 80% $1.00 $10 $100 Cost per task, log scale GPT-6 Astra, max Claude Opus 5.5, max

Source: Official Terminal-Bench-Science leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
GPT-6 Astra max Codex 68.1% $24
Claude Opus 5.5 max Claude Code 63.3% $23
Claude Fable 5.1 max Claude Code 40% $30
Claude Opus 5 max Claude Code 30% $33
GPT-5.6 Sol max Codex 22.4% $20
Claude Fable 5 max Claude Code 21.4% $68
DeepSeek V4.1 Flash max Codex 15.7% $1.84
Grok 4.7 xhigh Grok Build 14.3% $15
Gemini 3.8 Flash high mini-SWE-agent 12.4% $5.32
Claude Opus 4.8 max Claude Code 10.5% $28
GPT-5.6 Terra max Codex 8.57% $9.45
GLM-5.3 max Claude Code 8.10% $13
Kimi K3 max Claude Code 7.14% $7.26
Grok 4.6 xhigh Grok Build 7.14% $16
Gemini 3.7 Flash high mini-SWE-agent 5.71% $6.17
DeepSeek-V4-Pro max Codex 3.81% $5.33
GPT-5.6 Luna max Codex 3.33% $1.82

3 models have held number one on the official leaderboard since its release in August 2026 4 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.

Anthropic OpenAI Google DeepMind
Own leaderboard Not tested since Sep 2026
GPT-6 Astra 68.1%
Lab claims 4 leaders
Claude Fable 5.2 74.6%

Sources: Official Terminal-Bench-Science 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 2027 Near the ceiling (85%) Claude Fable 5.2 GPT-6 Astra Claude Fable 5.1 Claude Opus 5 GPT-5.6 Sol Claude Opus 4.8 DeepSeek-V4-Pro 0% 20% 40% 60% 80% 100% 2026 2027 Near the ceiling (85%) Claude Fable 5.2 GPT-6 Astra

Sources: Official Terminal-Bench-Science 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
OpenAI
Google DeepMind
Moonshot AI
Tencent
Thinking Machines
DateLaunch postScoreAs the post writes it
Nov 9, 2026 Claude Fable 5.2 74.6 Agentic scientific research Terminal-Bench-Science 0.1, Fable 5.2 with safeguards, max effort (launch table)
Nov 5, 2026 Inkling 2 Small 5.7 Terminal Bench Science v0.1
Nov 4, 2026 Tencent Hy4 19.8 Terminal Bench Science 0.1
Oct 28, 2026 Gemini 4 Carbon 64.8 Terminal-Bench-Science 0.1 (AA)
Oct 26, 2026 GPT-6.1 Terra Terminal-Bench-Science 0.1, max reasoning (chart)
Oct 24, 2026 Kimi K3.1 Pro 38.1 Terminal-Bench-Science 0.1 (Claude Code)
Oct 13, 2026 Gemini 4 Argon 57.6 Terminal-Bench Science 0.1
Sep 29, 2026 GPT-6.1 Sol 57 Terminal-Bench Science 0.1 (GPT-6.1 Sol Max)
Sep 22, 2026 Claude Opus 5.5 58.7 Agentic scientific research Terminal-Bench-Science 0.1
Sep 3, 2026 GPT-6 Astra 64.6 Terminal-Bench Science 0.1
Sep 1, 2026 Claude Fable 5.1 52.6 Agentic scientific research Terminal-Bench-Science 0.1

6 system cards report it, from 2 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
Nov 9, 2026 Claude Fable 5.2 system card 74.6 Terminal-Bench-Science 0.1, safeguards enabled, Claude Code --bare, max effort, no internet access, 10 trials per task. Mythos-only score 75.3% excluded (Section 8.6) Capabilities
Oct 13, 2026 Gemini 4 Argon model card 57.6 Terminal-Bench Science 0.1 (results table, p.5) Capabilities
Oct 7, 2026 Claude Haiku 5.5 system card 20.6 Terminal-Bench-Science 0.1, max effort, safeguards on with no fallback (8.5) Capabilities
Sep 28, 2026 Claude Sonnet 5.5 system card 59.9 Terminal-Bench-Science 0.1, max effort, Claude Code --bare mode (8.6) Capabilities
Sep 22, 2026 Claude Opus 5.5 system card 58.7 Terminal-Bench-Science 0.1, max effort, Claude Code --bare mode, safeguards with fallback, 10 trials per task (Table 8.1.A, 8.6) Capabilities
Sep 1, 2026 Claude Fable 5.1 system card 52.6 Terminal-Bench-Science 0.1, Claude Code --bare mode, max effort, 10 trials per task (Table 8.1.A, 8.7) 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
Claude Fable 5.1 52.6% Agentic scientific research Terminal-Bench-Science 0.1 40% Leaderboard, max, Claude Code +13 pts
Claude Opus 5.5 58.7% Agentic scientific research Terminal-Bench-Science 0.1 63.3% Leaderboard, max, Claude Code −4.6 pts
GPT-6 Astra 64.6% Terminal-Bench Science 0.1 68.1% Leaderboard, max, Codex −3.5 pts

More in Science and reasoning

All 92 in Science and reasoning
  • GPQA Diamond In use 198 graduate-level 'Google-proof' multiple-choice questions in biology, chemistry and physics. Gemini 4 Carbon 96.5%
  • FrontierScience In use Models solve physics, chemistry, and biology problems in an Olympiad track graded by short answer and a Research track graded by 10-point rubrics. Intern-S2-397B 87%
  • BioMysteryBench In use Bioinformatics problems on anonymized real datasets that require real analysis with tools. Rubric-graded, with human-solvable and human-difficult splits. Claude Fable 5.2 83.7%
  • HiPhO In use Models solve theory problems from 2024 and 2025 physics olympiad exams, some with diagrams. Official marking schemes grade answers and steps, mapped to medal levels. Gemini 3 Pro 78.3%
  • LABBench2 In use 11 biology research sub-tasks (literature, figures, tables, patents, trials and more) with tool access. Macro-averaged accuracy. GPT-5.2 60.9%
  • SGI-Bench In use Models work through more than 1,000 expert samples in four scientist tasks: deep research, idea generation, dry and wet experiments, and experimental reasoning. Gemini 3 Pro 33.8%