Benchmark Almanac

Frontier Agentic STEM

GPT-5.6 Sol 55.1% leads since August 2026
Not in model cards

Agents produce scientific results in a terminal. Task verifiers recompute the expected results from the underlying data.

Turing reports outcomes for five models on 805 tasks.

Made by
Turing
Released
August 2026
Kind
Research science
Level
Expert
Scored
Checked automatically
Answers
Agent task
Tasks
Kept private
Measures
Capability
In and out
Text → Actions, Text
Interaction
Agentic
Environment
Terminal
Refresh
One fixed set
Run by
A host
In views
Agents
Strongest model tested
Claude Opus 5 #11 on the capability index
Last model added
July 2026
Scores refreshed
November 20th, 2026
5
Models scored on its own leaderboard

GPT-5.6 Sol leads with 55.1% among models released by July 2026

Best score per model from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best.

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

  1. 1 GPT-5.6 Sol high 55.1%
  2. 2 Claude Opus 5 high 54.4%
  3. 3 GPT-5.5 medium 45.5%
  4. 4 Claude Opus 4.8 high 43.2%
  5. 5 Gemini 3.5 Flash medium 30.6%

Source: Official Frontier Agentic STEM leaderboard

#ModelScore ±SettingDateSource
1 GPT-5.6 Sol 55.1% ±0.6 high, Terminus-2 Jul 2026 Official leaderboard
2 Claude Opus 5 54.4% ±0.6 high, Terminus-2 Jul 2026 Official leaderboard
3 GPT-5.5 45.5% ±0.6 medium, Terminus-2 Apr 2026 Official leaderboard
4 Claude Opus 4.8 43.2% ±0.6 high, Terminus-2 May 2026 Official leaderboard
5 Gemini 3.5 Flash 30.6% ±0.6 medium, Terminus-2 May 2026 Official leaderboard

Rankings by part

We read 12 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as Physics, Biology and Mathematics. GPT-5.6 Sol leads 6 of them, and 2 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.

Physics

5 models we track have a score here.

  1. 1 GPT-5.6 Sol 39.9%
  2. 2 Claude Opus 5 39.2%
  3. 3 GPT-5.5 29.7%
  4. 4 Claude Opus 4.8 27.9%
  5. 5 Gemini 3.5 Flash 14.6%

Number one over time

Lab claims count from the day the card came out, independent runs from the model’s release.

OpenAI
Own leaderboard Not tested since Aug 2026
GPT-5.6 Sol 55.1%

Source: Official Frontier Agentic STEM leaderboard

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 Best so far
0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) GPT-5.6 Sol GPT-5.5 0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) GPT-5.6 Sol GPT-5.5

Source: Official Frontier Agentic STEM leaderboard

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

More in Science and reasoning

All 203 in Science and reasoning
  • GPQA Diamond In use 198 graduate-level 'Google-proof' multiple-choice questions in biology, chemistry and physics. Gemini 4 Carbon 97%
  • Terminal-Bench-Science In use 70 scientific research-workflow tasks across five science areas, run in Harbor containers. Hidden tests give the resolution rate. GPT-6 Astra 68.1%
  • 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%
  • 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%
  • 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%

Data audit

All 10 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access The tasks are private.
  • Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
  • Pass Independent runs Scores from the official leaderboard (5 entries).
  • Pass Models scored 5 models we track.
  • Pass Newest score The newest is from July 2026, for Claude Opus 5.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Claude Opus 5 (#11).
  • Pass Headroom The best is 55.1%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on labs.turing.com: 5 rows for models we track at the last read.
  • Pass Last read November 20th, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check