Benchmark Almanac

ThermoQA

Claude Opus 4.6 94.1% leads since March 2026
Not in model cards

Models calculate fluid properties and analyze thermodynamic components and cycles. A model extracts the answers, and a program checks values against reference tolerances.

Olivenet ranks six models on 293 questions. The composite weights each tier by its question count and averages scores across three runs.

Made by
Olivenet
Released
March 2026
Kind
Science questions
Level
University
Scored
Checked automatically
Answers
Short answer
Tasks
All public
Measures
Capability
Language
English
In and out
Text → Text
Interaction
Single turn
Items from
Generated
Run by
Anyone
Strongest model tested
GPT-5.4 #28 on the capability index
Last model added
March 2026
Scores refreshed
November 20th, 2026
6
Models scored on its own leaderboard

Claude Opus 4.6 leads with 94.1% among models released by March 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 March 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 Claude Opus 4.6 94.1%
  2. 2 GPT-5.4 93.1%
  3. 3 Gemini 3.1 Pro 92.5%
  4. 4 DeepSeek-R1 May 2025 87.4%
  5. 5 Grok 4 87.3%
  6. 6 MiniMax-M2.5 73%

Source: Official ThermoQA leaderboard

#ModelScoreSettingDateSource
1 Claude Opus 4.6 94.1% Feb 2026 Official leaderboard
2 GPT-5.4 93.1% Mar 2026 Official leaderboard
3 Gemini 3.1 Pro 92.5% Feb 2026 Official leaderboard
4 DeepSeek-R1 May 2025 87.4% May 2025 Official leaderboard
5 Grok 4 87.3% Jul 2025 Official leaderboard
6 MiniMax-M2.5 73% Feb 2026 Official leaderboard

Rankings by part

We read 21 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as Tier 1, Tier 1: Easy and Tier 1: Medium. Gemini 3.1 Pro leads 6 of them, and 5 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.

Tier 1

6 models we track have a score here.

  1. 1 Gemini 3.1 Pro ↑2 97.9%
  2. 2 GPT-5.4 97.8%
  3. 3 Claude Opus 4.6 ↓2 96.4%
  4. 4 Grok 4 ↑1 91.8%
  5. 5 DeepSeek-R1 May 2025 ↓1 90.5%
  6. 6 MiniMax-M2.5 85.2%

Number one over time

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

Anthropic
Own leaderboard Passed 85% in Mar 2026, by Claude Opus 4.6

Source: Official ThermoQA leaderboard

DeepSeek-R1 on the official leaderboard passed 85% in May 2025

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
On the benchmark’s own leaderboard Best so far
0% 20% 40% 60% 80% 100% 2025 2026 Near the ceiling (85%) Claude Opus 4.6 DeepSeek-R1 0% 20% 40% 60% 80% 100% 2025 2026 Near the ceiling (85%) Claude Opus 4.6 DeepSeek-R1

Source: Official ThermoQA 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 official leaderboard (6 entries).
  • Pass Models scored 6 models we track.
  • Note Newest score The newest came 8 months ago, in March 2026, for GPT-5.4. That’s expected for a saturated test.
  • Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is GPT-5.4 (#28).
  • Note Headroom Saturated. The best is 94.1%, past 85% since May 2025.
Leaderboard import 3 pass
  • Pass Importer We read the board on huggingface.co: 6 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