Benchmark Almanac

CompMat-Bench

GPT-5.6 Sol 91.5% leads since September 2026
Not in model cards

Agents complete individual steps from published computational materials studies. Fixed rules compare their inputs and outputs with results reproduced by the authors.

Made by
Chenmu Zhang and colleagues
Released
September 2026
Kind
Lab and data work
Level
Expert
Scored
Checked automatically
Answers
Agent task
Tasks
All public
Measures
Capability
Language
English
In and out
Text, Code → Text, Code, Actions
Interaction
Agentic
Environment
Terminal
Items from
Real work and use
Refresh
One fixed set
Run by
Anyone
Strongest model tested
GPT-5.6 Sol #14 on the capability index
Last model added
September 2026
Scores refreshed
November 20th, 2026
3
Models scored in its paper

GPT-5.6 Sol leads with 91.5% among models released by September 2026

Best score per model from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. Where a model ran with several settings or harnesses, we keep its best.

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:

  1. 1 GPT-5.6 Sol Full guidance 91.5%
  2. 2 Gemini 3.8 Flash Full guidance 89.4%
  3. 3 DeepSeek V4.1 Flash Full guidance 66%

Source: The CompMat-Bench paper

#ModelScoreSettingDateSource
1 GPT-5.6 Sol 91.5% Full guidance, Codex CLI Jul 2026 Official leaderboard
2 Gemini 3.8 Flash 89.4% Full guidance, MatClaw Sep 2026 Official leaderboard
3 DeepSeek V4.1 Flash 66% Full guidance, MatClaw Sep 2026 Official leaderboard

Rankings by part

We read 6 parts from the benchmark’s paper, each ranking models on one part of the test, such as Prepare inputs, Analyze outputs and Run and analyze. GPT-5.6 Sol leads 5 of them, and Gemini 3.8 Flash leads the other one. Arrows show how far a model moved from its overall rank among the models we track.

Prepare inputs

3 models we track have a score here.

  1. 1 GPT-5.6 Sol 76.7%
  2. 2 Gemini 3.8 Flash 70%
  3. 3 DeepSeek V4.1 Flash 36.7%

Number one over time

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

OpenAI
Benchmark paper Passed 85% in Sep 2026, by GPT-5.6 Sol
GPT-5.6 Sol 91.5%

Source: The CompMat-Bench paper

GPT-5.6 Sol on the official leaderboard passed 85% in July 2026

Models released before it came out already scored that high. All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
In the benchmark’s paper
0% 20% 40% 60% 80% 100% Near the ceiling (85%) GPT-5.6 Sol 0% 20% 40% 60% 80% 100% Near the ceiling (85%) GPT-5.6 Sol

Source: Official CompMat-Bench 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 8 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
  • Pass Independent runs Scores from the benchmark’s paper (3 entries).
  • Note Models scored Only 3 models we track.
  • Pass Newest score The newest is from September 2026, for DeepSeek V4.1 Flash.
  • Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is GPT-5.6 Sol (#14).
  • Note Headroom Saturated. The best is 91.5%, past 85% since July 2026.
Leaderboard import 3 pass
  • Pass Importer We read the board on github.com: 4 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