LLM Physics Plotting Benchmark
Models write Python code to produce requested plots from ATLAS collision data. Each trial passes when the code runs and meets the configured checks.
The default workflow reports 3,138 trials across 20 model configurations and 18 questions. The report includes costs and separates plotting workflows.
- Made by
- Gordon Watts
- Released
- September 2025
- Kind
- Lab and data work
- Level
- University
- Scored
- Checked automatically
- Answers
- Code
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Environment
- Code sandbox
- 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
- July 2026
- Scores refreshed
- November 20th, 2026
GPT-5.2 Codex leads with 90.6% among models released by July 2026 GPT-5.2 Codex leads with 90.6% among models released by July 2026
Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Every run is in the next chart. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at 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:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 15 more
- 90.6 GPT-5.2 Codex
- 85.6 GPT-5.2
- 85.6 GPT-5.6 Luna
- 85.6 GPT-5.6 Sol
- 85.0 GPT-5 mini
- 84.6 kimi-k27-nrp
- 83.0 GLM-5
- 82.2
Gemini 2.5 Pro
- 80.6 Kimi K2.5
- 74.4 Claude Sonnet 4.5
- 73.9 Claude Opus 4.6
- 73.3
Gemini 3 Flash
- 65.0
MiniMax-M2.5
- 61.1 Qwen3.5-nrp
- 60.6 gpt-oss-120b
- 60.6 grok-code-fast-1
- 53.9
DeepSeek-V3.2
- 45.0 gpt-oss-20b
- 25.0
Llama 3.3 70B
- 1 GPT-5.2 Codex ServiceX + Awkward Array + Hist · Combined current + historical contexts 90.6%
- 2 GPT-5.2 ServiceX + Awkward Array + Hist · Combined current + historical contexts 85.6%
- 3 GPT-5.6 Luna ServiceX + Awkward Array + Hist · Combined current + historical contexts 85.6%
- 4 GPT-5.6 Sol ServiceX + Awkward Array + Hist · Combined current + historical contexts 85.6%
- 5 GPT-5 mini ServiceX + Awkward Array + Hist · Combined current + historical contexts 85%
- 6 kimi-k27-nrp ServiceX + Awkward Array + Hist · Combined current + historical contexts 84.6%
- 7 GLM-5 ServiceX + ROOT RDataFrame · Combined recorded contexts 83%
- 8
Gemini 2.5 Pro Jun 2025, ServiceX + Awkward Array + Hist · Combined current + historical contexts 82.2%
- 9 Kimi K2.5 ServiceX + Awkward Array + Hist · Combined current + historical contexts 80.6%
- 10 Claude Sonnet 4.5 ServiceX + Awkward Array + Hist · Combined current + historical contexts 74.4%
- 11 Claude Opus 4.6 ServiceX + Awkward Array + Hist · Combined current + historical contexts 73.9%
- 12
Gemini 3 Flash ServiceX + Awkward Array + Hist · Combined current + historical contexts 73.3%
- 13
MiniMax-M2.5 ServiceX + Awkward Array + Hist · Combined current + historical contexts 65%
- 14 Qwen3.5-nrp ServiceX + Awkward Array + Hist · Combined current + historical contexts 61.1%
- 15 gpt-oss-120b ServiceX + Awkward Array + Hist · Combined current + historical contexts 60.6%
- 16 grok-code-fast-1 ServiceX + Awkward Array + Hist · Combined current + historical contexts 60.6%
- 17
DeepSeek-V3.2 ServiceX + Awkward Array + Hist · Combined current + historical contexts 53.9%
- 18 gpt-oss-20b ServiceX + Awkward Array + Hist · Combined current + historical contexts 45%
- 19
Llama 3.3 70B ServiceX + Awkward Array + Hist · Combined current + historical contexts 25%
Source: Official LLM Physics Plotting Benchmark leaderboard
- 90.6 GPT-5.2 Codex
- 85.6 GPT-5.2
- 85.6 GPT-5.6 Luna
- 85.6 GPT-5.6 Sol
- 85.0 GPT-5 mini
- 83.0 GLM-5
- 82.2
Gemini 2.5 Pro
- 80.6 Kimi K2.5
- 74.4 Claude Sonnet 4.5
- 73.9 Claude Opus 4.6
- 73.3
Gemini 3 Flash
- 65.0
MiniMax-M2.5
- 60.6 gpt-oss-120b
- 60.6 grok-code-fast-1
- 53.9
DeepSeek-V3.2
- 45.0 gpt-oss-20b
- 25.0
Llama 3.3 70B
- 1 GPT-5.2 Codex ServiceX + Awkward Array + Hist · Combined current + historical contexts 90.6%
- 2 GPT-5.2 ServiceX + Awkward Array + Hist · Combined current + historical contexts 85.6%
- 3 GPT-5.6 Luna ServiceX + Awkward Array + Hist · Combined current + historical contexts 85.6%
- 4 GPT-5.6 Sol ServiceX + Awkward Array + Hist · Combined current + historical contexts 85.6%
- 5 GPT-5 mini ServiceX + Awkward Array + Hist · Combined current + historical contexts 85%
- 6 GLM-5 ServiceX + ROOT RDataFrame · Combined recorded contexts 83%
- 7
Gemini 2.5 Pro Jun 2025, ServiceX + Awkward Array + Hist · Combined current + historical contexts 82.2%
- 8 Kimi K2.5 ServiceX + Awkward Array + Hist · Combined current + historical contexts 80.6%
- 9 Claude Sonnet 4.5 ServiceX + Awkward Array + Hist · Combined current + historical contexts 74.4%
- 10 Claude Opus 4.6 ServiceX + Awkward Array + Hist · Combined current + historical contexts 73.9%
- 11
Gemini 3 Flash ServiceX + Awkward Array + Hist · Combined current + historical contexts 73.3%
- 12
MiniMax-M2.5 ServiceX + Awkward Array + Hist · Combined current + historical contexts 65%
- 13 gpt-oss-120b ServiceX + Awkward Array + Hist · Combined current + historical contexts 60.6%
- 14 grok-code-fast-1 ServiceX + Awkward Array + Hist · Combined current + historical contexts 60.6%
- 15
DeepSeek-V3.2 ServiceX + Awkward Array + Hist · Combined current + historical contexts 53.9%
- 16 gpt-oss-20b ServiceX + Awkward Array + Hist · Combined current + historical contexts 45%
- 17
Llama 3.3 70B ServiceX + Awkward Array + Hist · Combined current + historical contexts 25%
Source: Official LLM Physics Plotting Benchmark leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-5.2 Codex | 90.6% | ServiceX + Awkward Array + Hist · Combined current + historical contexts | Dec 2025 | Official leaderboard |
| 2 | GPT-5.2 | 85.6% | ServiceX + Awkward Array + Hist · Combined current + historical contexts | Dec 2025 | Official leaderboard |
| 3 | GPT-5.6 Luna | 85.6% | ServiceX + Awkward Array + Hist · Combined current + historical contexts | Jul 2026 | Official leaderboard |
| 4 | GPT-5.6 Sol | 85.6% | ServiceX + Awkward Array + Hist · Combined current + historical contexts | Jul 2026 | Official leaderboard |
| 5 | GPT-5 mini | 85% | ServiceX + Awkward Array + Hist · Combined current + historical contexts | Aug 2025 | Official leaderboard |
| 6 | kimi-k27-nrp | 84.6% | ServiceX + Awkward Array + Hist · Combined current + historical contexts | Official leaderboard | |
| 7 | GLM-5 | 83% | ServiceX + ROOT RDataFrame · Combined recorded contexts | Feb 2026 | Official leaderboard |
| 8 | | 82.2% | ServiceX + Awkward Array + Hist · Combined current + historical contexts | Jun 2025 | Official leaderboard |
| 9 | Kimi K2.5 | 80.6% | ServiceX + Awkward Array + Hist · Combined current + historical contexts | Jan 2026 | Official leaderboard |
| 10 | Claude Sonnet 4.5 | 74.4% | ServiceX + Awkward Array + Hist · Combined current + historical contexts | Sep 2025 | Official leaderboard |
| 11 | Claude Opus 4.6 | 73.9% | ServiceX + Awkward Array + Hist · Combined current + historical contexts | Feb 2026 | Official leaderboard |
| 12 | | 73.3% | ServiceX + Awkward Array + Hist · Combined current + historical contexts | Dec 2025 | Official leaderboard |
| 13 | | 65% | ServiceX + Awkward Array + Hist · Combined current + historical contexts | Feb 2026 | Official leaderboard |
| 14 | Qwen3.5-nrp | 61.1% | ServiceX + Awkward Array + Hist · Combined current + historical contexts | Official leaderboard | |
| 15 | gpt-oss-120b | 60.6% | ServiceX + Awkward Array + Hist · Combined current + historical contexts | Aug 2025 | Official leaderboard |
| 16 | grok-code-fast-1 | 60.6% | ServiceX + Awkward Array + Hist · Combined current + historical contexts | Aug 2025 | Official leaderboard |
| 17 | | 53.9% | ServiceX + Awkward Array + Hist · Combined current + historical contexts | Dec 2025 | Official leaderboard |
| 18 | gpt-oss-20b | 45% | ServiceX + Awkward Array + Hist · Combined current + historical contexts | Aug 2025 | Official leaderboard |
| 19 | | 25% | ServiceX + Awkward Array + Hist · Combined current + historical contexts | Dec 2024 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-5.2 Codex | 90.6% | ServiceX + Awkward Array + Hist · Combined current + historical contexts | Dec 2025 | Official leaderboard |
| 2 | GPT-5.2 | 85.6% | ServiceX + Awkward Array + Hist · Combined current + historical contexts | Dec 2025 | Official leaderboard |
| 3 | GPT-5.6 Luna | 85.6% | ServiceX + Awkward Array + Hist · Combined current + historical contexts | Jul 2026 | Official leaderboard |
| 4 | GPT-5.6 Sol | 85.6% | ServiceX + Awkward Array + Hist · Combined current + historical contexts | Jul 2026 | Official leaderboard |
| 5 | GPT-5 mini | 85% | ServiceX + Awkward Array + Hist · Combined current + historical contexts | Aug 2025 | Official leaderboard |
| 6 | GLM-5 | 83% | ServiceX + ROOT RDataFrame · Combined recorded contexts | Feb 2026 | Official leaderboard |
| 7 | | 82.2% | ServiceX + Awkward Array + Hist · Combined current + historical contexts | Jun 2025 | Official leaderboard |
| 8 | Kimi K2.5 | 80.6% | ServiceX + Awkward Array + Hist · Combined current + historical contexts | Jan 2026 | Official leaderboard |
| 9 | Claude Sonnet 4.5 | 74.4% | ServiceX + Awkward Array + Hist · Combined current + historical contexts | Sep 2025 | Official leaderboard |
| 10 | Claude Opus 4.6 | 73.9% | ServiceX + Awkward Array + Hist · Combined current + historical contexts | Feb 2026 | Official leaderboard |
| 11 | | 73.3% | ServiceX + Awkward Array + Hist · Combined current + historical contexts | Dec 2025 | Official leaderboard |
| 12 | | 65% | ServiceX + Awkward Array + Hist · Combined current + historical contexts | Feb 2026 | Official leaderboard |
| 13 | gpt-oss-120b | 60.6% | ServiceX + Awkward Array + Hist · Combined current + historical contexts | Aug 2025 | Official leaderboard |
| 14 | grok-code-fast-1 | 60.6% | ServiceX + Awkward Array + Hist · Combined current + historical contexts | Aug 2025 | Official leaderboard |
| 15 | | 53.9% | ServiceX + Awkward Array + Hist · Combined current + historical contexts | Dec 2025 | Official leaderboard |
| 16 | gpt-oss-20b | 45% | ServiceX + Awkward Array + Hist · Combined current + historical contexts | Aug 2025 | Official leaderboard |
| 17 | | 25% | ServiceX + Awkward Array + Hist · Combined current + historical contexts | Dec 2024 | Official leaderboard |
Rankings by part
We read 18 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as Q1, Q2 and Q3. Gemini 2.5 Pro leads 8 of them, and 6 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.
Q1
17 models we track have a score here.
- 1
Gemini 2.5 Pro Jun 2025 ↑6 100%
- 2 gpt-oss-120b ↑11 100%
- 3 gpt-oss-20b ↑13 100%
- 4 GPT-5 mini ↑1 100%
- 5 grok-code-fast-1 ↑9 100%
- 6 Claude Sonnet 4.5 ↑3 100%
- 7
DeepSeek-V3.2 ↑8 100%
- 8 GPT-5.2 ↓6 100%
- 9
Gemini 3 Flash ↑2 100%
- 10 GPT-5.2 Codex ↓9 100%
Q2
17 models we track have a score here.
- 1
Gemini 2.5 Pro Jun 2025 ↑6 100%
- 2 GPT-5 mini ↑3 100%
- 3 grok-code-fast-1 ↑11 100%
- 4 Claude Sonnet 4.5 ↑5 100%
- 5
DeepSeek-V3.2 ↑10 100%
- 6 GPT-5.2 ↓4 100%
- 7
Gemini 3 Flash ↑4 100%
- 8 GPT-5.2 Codex ↓7 100%
- 9 Kimi K2.5 ↓1 100%
- 10 Claude Opus 4.6 100%
Q3
17 models we track have a score here.
- 1
Gemini 2.5 Pro Jun 2025 ↑6 100%
- 2 GPT-5 mini ↑3 100%
- 3 Claude Sonnet 4.5 ↑6 100%
- 4 GPT-5.2 ↓2 100%
- 5
Gemini 3 Flash ↑6 100%
- 6 GPT-5.2 Codex ↓5 100%
- 7 Kimi K2.5 ↑1 100%
- 8 Claude Opus 4.6 ↑2 100%
- 9 GLM-5 ↓3 100%
- 10
MiniMax-M2.5 ↑2 100%
Q4
17 models we track have a score here.
- 1
Gemini 2.5 Pro Jun 2025 ↑6 100%
- 2 gpt-oss-120b ↑11 100%
- 3 gpt-oss-20b ↑13 100%
- 4 GPT-5 mini ↑1 100%
- 5 grok-code-fast-1 ↑9 100%
- 6 Claude Sonnet 4.5 ↑3 100%
- 7
DeepSeek-V3.2 ↑8 100%
- 8 GPT-5.2 ↓6 100%
- 9
Gemini 3 Flash ↑2 100%
- 10 GPT-5.2 Codex ↓9 100%
Q5
17 models we track have a score here.
- 1 gpt-oss-120b ↑12 100%
- 2 GPT-5 mini ↑3 100%
- 3 Claude Sonnet 4.5 ↑6 100%
- 4 GPT-5.2 ↓2 100%
- 5 GPT-5.2 Codex ↓4 100%
- 6 Claude Opus 4.6 ↑4 100%
- 7 GLM-5 ↓1 100%
- 8 GPT-5.6 Luna ↓5 100%
- 9 GPT-5.6 Sol ↓5 100%
- 10
Gemini 3 Flash ↑1 90%
Q6
17 models we track have a score here.
- 1 GPT-5 mini ↑4 100%
- 2 GPT-5.2 100%
- 3 GPT-5.2 Codex ↓2 100%
- 4 Claude Opus 4.6 ↑6 90%
- 5
Gemini 2.5 Pro Jun 2025 ↑2 80%
- 6
Gemini 3 Flash ↑5 80%
- 7 Kimi K2.5 ↑1 80%
- 8 GLM-5 ↓2 80%
- 9
MiniMax-M2.5 ↑3 70%
- 10 grok-code-fast-1 ↑4 40%
Q7
17 models we track have a score here.
- 1 GPT-5 mini ↑4 100%
- 2 GPT-5.2 100%
- 3 GPT-5.2 Codex ↓2 100%
- 4 Kimi K2.5 ↑4 100%
- 5 GPT-5.6 Luna ↓2 100%
- 6 GPT-5.6 Sol ↓2 100%
- 7
Gemini 2.5 Pro Jun 2025 90%
- 8 GLM-5 ↓2 90%
- 9 Claude Sonnet 4.5 70%
- 10
Gemini 3 Flash ↑1 70%
Q8
17 models we track have a score here.
- 1 GPT-5.2 ↑1 100%
- 2 Claude Opus 4.6 ↑8 100%
- 3 GLM-5 ↑3 100%
- 4 GPT-5.6 Luna ↓1 100%
- 5 GPT-5.6 Sol ↓1 100%
- 6 GPT-5 mini ↓1 90%
- 7 Kimi K2.5 ↑1 90%
- 8 GPT-5.2 Codex ↓7 80%
- 9 Claude Sonnet 4.5 70%
- 10
Gemini 3 Flash ↑1 60%
Q16
17 models we track have a score here.
- 1
DeepSeek-V3.2 ↑14 80%
- 2 GPT-5.2 Codex ↓1 80%
- 3 GPT-5.2 ↓1 70%
- 4
Gemini 3 Flash ↑7 70%
- 5 GPT-5.6 Luna ↓2 70%
- 6 GPT-5.6 Sol ↓2 70%
- 7 GPT-5 mini ↓2 60%
- 8
Gemini 2.5 Pro Jun 2025 ↓1 50%
- 9 gpt-oss-120b ↑4 30%
- 10 GLM-5 ↓4 30%
Q9
15 models we track have a score here.
- 1 GPT-5.2 ↑1 100%
- 2 Kimi K2.5 ↑6 100%
- 3 Claude Opus 4.6 ↑7 100%
- 4 GLM-5 ↑2 100%
- 5
Gemini 2.5 Pro Jun 2025 ↑2 90%
- 6 gpt-oss-20b ↑10 90%
- 7 gpt-oss-120b ↑6 80%
- 8 GPT-5 mini ↓3 80%
- 9 grok-code-fast-1 ↑5 80%
- 10 GPT-5.2 Codex ↓9 80%
Q10
15 models we track have a score here.
- 1
Gemini 3 Flash ↑10 100%
- 2 GLM-5 ↑4 90%
- 3 Claude Sonnet 4.5 ↑6 80%
- 4
Gemini 2.5 Pro Jun 2025 ↑3 70%
- 5 grok-code-fast-1 ↑9 60%
- 6 GPT-5.2 ↓4 60%
- 7
DeepSeek-V3.2 ↑8 50%
- 8 GPT-5.2 Codex ↓7 40%
- 9
MiniMax-M2.5 ↑3 40%
- 10 Kimi K2.5 ↓2 30%
Q11
15 models we track have a score here.
- 1
Gemini 2.5 Pro Jun 2025 ↑6 100%
- 2 gpt-oss-120b ↑11 100%
- 3 GPT-5 mini ↑2 100%
- 4 Claude Sonnet 4.5 ↑5 100%
- 5 GPT-5.2 ↓3 100%
- 6
Gemini 3 Flash ↑5 100%
- 7 GPT-5.2 Codex ↓6 100%
- 8 Kimi K2.5 100%
- 9 Claude Opus 4.6 ↑1 100%
- 10 GLM-5 ↓4 100%
Q12
15 models we track have a score here.
- 1 GPT-5.2 ↑1 100%
- 2 GPT-5.2 Codex ↓1 100%
- 3 GLM-5 ↑3 90%
- 4
MiniMax-M2.5 ↑8 90%
- 5 Kimi K2.5 ↑3 80%
- 6
Gemini 2.5 Pro Jun 2025 ↑1 70%
- 7 Claude Sonnet 4.5 ↑2 50%
- 8 gpt-oss-120b ↑5 40%
- 9 GPT-5 mini ↓4 40%
- 10 grok-code-fast-1 ↑4 20%
Q13
15 models we track have a score here.
- 1
Gemini 2.5 Pro Jun 2025 ↑6 100%
- 2 gpt-oss-20b ↑14 100%
- 3
MiniMax-M2.5 ↑9 100%
- 4 GPT-5 mini ↑1 90%
- 5 GPT-5.2 ↓3 90%
- 6 Kimi K2.5 ↑2 90%
- 7 GLM-5 ↓1 80%
- 8 GPT-5.2 Codex ↓7 70%
- 9 gpt-oss-120b ↑4 50%
- 10 grok-code-fast-1 ↑4 40%
Q14
15 models we track have a score here.
- 1
Gemini 2.5 Pro Jun 2025 ↑6 100%
- 2 gpt-oss-120b ↑11 100%
- 3 GPT-5 mini ↑2 100%
- 4 Claude Sonnet 4.5 ↑5 100%
- 5 GPT-5.2 ↓3 100%
- 6
Gemini 3 Flash ↑5 100%
- 7 GPT-5.2 Codex ↓6 100%
- 8 Kimi K2.5 100%
- 9 Claude Opus 4.6 ↑1 100%
- 10 grok-code-fast-1 ↑4 90%
Q15
15 models we track have a score here.
- 1 Claude Opus 4.6 ↑9 90%
- 2 GPT-5 mini ↑3 80%
- 3 GPT-5.2 Codex ↓2 80%
- 4 GPT-5.2 ↓2 70%
- 5 gpt-oss-20b ↑11 60%
- 6 gpt-oss-120b ↑7 50%
- 7 grok-code-fast-1 ↑7 50%
- 8 Claude Sonnet 4.5 ↑1 50%
- 9 Kimi K2.5 ↓1 50%
- 10
Gemini 2.5 Pro Jun 2025 ↓3 40%
Q17
15 models we track have a score here.
- 1 GPT-5.2 ↑1 100%
- 2
Gemini 3 Flash ↑9 100%
- 3 GPT-5.2 Codex ↓2 100%
- 4 Claude Opus 4.6 ↑6 100%
- 5 GLM-5 ↑1 100%
- 6
Gemini 2.5 Pro Jun 2025 ↑1 90%
- 7 GPT-5 mini ↓2 90%
- 8 Claude Sonnet 4.5 ↑1 80%
- 9 Kimi K2.5 ↓1 80%
- 10
MiniMax-M2.5 ↑2 80%
Q18
15 models we track have a score here.
- 1
Gemini 2.5 Pro Jun 2025 ↑6 100%
- 2 GPT-5 mini ↑3 100%
- 3 Claude Sonnet 4.5 ↑6 100%
- 4 GPT-5.2 ↓2 100%
- 5 GPT-5.2 Codex ↓4 100%
- 6 Claude Opus 4.6 ↑4 100%
- 7 GLM-5 ↓1 100%
- 8
MiniMax-M2.5 ↑4 100%
- 9 Kimi K2.5 ↓1 90%
- 10 grok-code-fast-1 ↑4 70%
The best score, 90.6%, costs $0.10 a task
Runs on the cost frontier score higher than any run that's cheaper. GPT-5.6 Luna at ServiceX + Awkward Array + Hist · Combined current + historical contexts comes within 5 points of the best for $0.03 a task, 3 times cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.
Source: Official LLM Physics Plotting Benchmark leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| GPT-5.2 Codex | ServiceX + Awkward Array + Hist · Combined current + historical contexts | 90.6% | $0.10 | ||
| GPT-5.2 Codex | ServiceX + Awkward Array + Hist · Historical import · legacy-d63e64dde22b | 90.6% | $0.10 | ||
| GPT-5.2 | ServiceX + Awkward Array + Hist · Combined current + historical contexts | 85.6% | $0.08 | ||
| GPT-5.2 | ServiceX + Awkward Array + Hist · Historical import · legacy-d63e64dde22b | 85.6% | $0.08 | ||
| GPT-5.6 Luna | ServiceX + Awkward Array + Hist · Combined current + historical contexts | 85.6% | $0.03 | ||
| GPT-5.6 Luna | ServiceX + Awkward Array + Hist · Current · 6261ce9ab00198a1 | 85.6% | $0.03 | ||
| GPT-5.6 Sol | ServiceX + Awkward Array + Hist · Combined current + historical contexts | 85.6% | $0.33 | ||
| GPT-5.6 Sol | ServiceX + Awkward Array + Hist · Current · 6261ce9ab00198a1 | 85.6% | $0.33 | ||
| GPT-5 mini | ServiceX + Awkward Array + Hist · Combined current + historical contexts | 85% | $0.04 | ||
| GPT-5 mini | ServiceX + Awkward Array + Hist · Historical import · legacy-d63e64dde22b | 85% | $0.04 | ||
| GPT-5.6 Luna | ServiceX + Awkward Array + Hist · Combined current + historical contexts | 84.4% | $0.05 | ||
| GPT-5.6 Luna | ServiceX + Awkward Array + Hist · Current · 6261ce9ab00198a1 | 84.4% | $0.05 | ||
| GLM-5 | ServiceX + ROOT RDataFrame · Combined recorded contexts | 83% | $0.06 | ||
| GLM-5 | ServiceX + ROOT RDataFrame · Historical import · legacy-b55696a333ff | 83% | $0.06 | ||
| ServiceX + Awkward Array + Hist · Combined current + historical contexts | 82.2% | $0.27 | |||
| ServiceX + Awkward Array + Hist · Historical import · legacy-d63e64dde22b | 82.2% | $0.27 | |||
| GLM-5 | ServiceX + Awkward Array + Hist · Combined current + historical contexts | 81.1% | $0.08 | ||
| GLM-5 | ServiceX + Awkward Array + Hist · Historical import · legacy-d63e64dde22b | 81.1% | $0.08 | ||
| Kimi K2.5 | ServiceX + Awkward Array + Hist · Combined current + historical contexts | 80.6% | $0.06 | ||
| Kimi K2.5 | ServiceX + Awkward Array + Hist · Historical import · legacy-d63e64dde22b | 80.6% | $0.06 | ||
| GPT-5 mini | ServiceX + ROOT RDataFrame · Combined recorded contexts | 77% | $0.02 | ||
| GPT-5 mini | ServiceX + ROOT RDataFrame · Historical import · legacy-b55696a333ff | 77% | $0.02 | ||
| Claude Sonnet 4.5 | ServiceX + Awkward Array + Hist · Combined current + historical contexts | 74.4% | $0.22 | ||
| Claude Sonnet 4.5 | ServiceX + Awkward Array + Hist · Historical import · legacy-d63e64dde22b | 74.4% | $0.22 | ||
| GPT-5.2 | ServiceX + ROOT RDataFrame · Combined recorded contexts | 74% | $0.07 | ||
| GPT-5.2 | ServiceX + ROOT RDataFrame · Historical import · legacy-b55696a333ff | 74% | $0.07 | ||
| Claude Opus 4.6 | ServiceX + Awkward Array + Hist · Combined current + historical contexts | 73.9% | $0.28 | ||
| Claude Opus 4.6 | ServiceX + Awkward Array + Hist · Historical import · legacy-d63e64dde22b | 73.9% | $0.28 | ||
| ServiceX + Awkward Array + Hist · Combined current + historical contexts | 73.3% | $0.04 | |||
| ServiceX + Awkward Array + Hist · Historical import · legacy-d63e64dde22b | 73.3% | $0.04 | |||
| Kimi K2.5 | ServiceX + ROOT RDataFrame · Combined recorded contexts | 72% | $0.05 | ||
| Kimi K2.5 | ServiceX + ROOT RDataFrame · Historical import · legacy-b55696a333ff | 72% | $0.05 | ||
| ServiceX + Awkward Array + Hist · Combined current + historical contexts | 65% | $0.05 | |||
| ServiceX + Awkward Array + Hist · Historical import · legacy-d63e64dde22b | 65% | $0.05 | |||
| gpt-oss-120b | ServiceX + Awkward Array + Hist · Combined current + historical contexts | 60.6% | $0.03 | ||
| gpt-oss-120b | ServiceX + Awkward Array + Hist · Historical import · legacy-d63e64dde22b | 60.6% | $0.03 | ||
| grok-code-fast-1 | ServiceX + Awkward Array + Hist · Combined current + historical contexts | 60.6% | $0.06 | ||
| grok-code-fast-1 | ServiceX + Awkward Array + Hist · Historical import · legacy-d63e64dde22b | 60.6% | $0.06 | ||
| ServiceX + Awkward Array + Hist · Combined current + historical contexts | 53.9% | $0.04 | |||
| ServiceX + Awkward Array + Hist · Historical import · legacy-d63e64dde22b | 53.9% | $0.04 | |||
| gpt-oss-20b | ServiceX + Awkward Array + Hist · Combined current + historical contexts | 45% | $0.02 | ||
| gpt-oss-20b | ServiceX + Awkward Array + Hist · Historical import · legacy-d63e64dde22b | 45% | $0.02 | ||
| ServiceX + Awkward Array + Hist · Combined current + historical contexts | 25% | $0.03 | |||
| ServiceX + Awkward Array + Hist · Historical import · legacy-d63e64dde22b | 25% | $0.03 |
The best score, 90.6%, costs $0.10 a task
Runs on the cost frontier score higher than any run that's cheaper. GPT-5.6 Luna at ServiceX + Awkward Array + Hist · Combined current + historical contexts comes within 5 points of the best for $0.03 a task, 3 times cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.
Source: Official LLM Physics Plotting Benchmark leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| GPT-5.2 Codex | ServiceX + Awkward Array + Hist · Combined current + historical contexts | 90.6% | $0.10 | ||
| GPT-5.2 Codex | ServiceX + Awkward Array + Hist · Historical import · legacy-d63e64dde22b | 90.6% | $0.10 | ||
| GPT-5.2 | ServiceX + Awkward Array + Hist · Combined current + historical contexts | 85.6% | $0.08 | ||
| GPT-5.2 | ServiceX + Awkward Array + Hist · Historical import · legacy-d63e64dde22b | 85.6% | $0.08 | ||
| GPT-5.6 Luna | ServiceX + Awkward Array + Hist · Combined current + historical contexts | 85.6% | $0.03 | ||
| GPT-5.6 Luna | ServiceX + Awkward Array + Hist · Current · 6261ce9ab00198a1 | 85.6% | $0.03 | ||
| GPT-5.6 Sol | ServiceX + Awkward Array + Hist · Combined current + historical contexts | 85.6% | $0.33 | ||
| GPT-5.6 Sol | ServiceX + Awkward Array + Hist · Current · 6261ce9ab00198a1 | 85.6% | $0.33 | ||
| GPT-5 mini | ServiceX + Awkward Array + Hist · Combined current + historical contexts | 85% | $0.04 | ||
| GPT-5 mini | ServiceX + Awkward Array + Hist · Historical import · legacy-d63e64dde22b | 85% | $0.04 | ||
| GPT-5.6 Luna | ServiceX + Awkward Array + Hist · Combined current + historical contexts | 84.4% | $0.05 | ||
| GPT-5.6 Luna | ServiceX + Awkward Array + Hist · Current · 6261ce9ab00198a1 | 84.4% | $0.05 | ||
| GLM-5 | ServiceX + ROOT RDataFrame · Combined recorded contexts | 83% | $0.06 | ||
| GLM-5 | ServiceX + ROOT RDataFrame · Historical import · legacy-b55696a333ff | 83% | $0.06 | ||
| ServiceX + Awkward Array + Hist · Combined current + historical contexts | 82.2% | $0.27 | |||
| ServiceX + Awkward Array + Hist · Historical import · legacy-d63e64dde22b | 82.2% | $0.27 | |||
| GLM-5 | ServiceX + Awkward Array + Hist · Combined current + historical contexts | 81.1% | $0.08 | ||
| GLM-5 | ServiceX + Awkward Array + Hist · Historical import · legacy-d63e64dde22b | 81.1% | $0.08 | ||
| Kimi K2.5 | ServiceX + Awkward Array + Hist · Combined current + historical contexts | 80.6% | $0.06 | ||
| Kimi K2.5 | ServiceX + Awkward Array + Hist · Historical import · legacy-d63e64dde22b | 80.6% | $0.06 | ||
| GPT-5 mini | ServiceX + ROOT RDataFrame · Combined recorded contexts | 77% | $0.02 | ||
| GPT-5 mini | ServiceX + ROOT RDataFrame · Historical import · legacy-b55696a333ff | 77% | $0.02 | ||
| Claude Sonnet 4.5 | ServiceX + Awkward Array + Hist · Combined current + historical contexts | 74.4% | $0.22 | ||
| Claude Sonnet 4.5 | ServiceX + Awkward Array + Hist · Historical import · legacy-d63e64dde22b | 74.4% | $0.22 | ||
| GPT-5.2 | ServiceX + ROOT RDataFrame · Combined recorded contexts | 74% | $0.07 | ||
| GPT-5.2 | ServiceX + ROOT RDataFrame · Historical import · legacy-b55696a333ff | 74% | $0.07 | ||
| Claude Opus 4.6 | ServiceX + Awkward Array + Hist · Combined current + historical contexts | 73.9% | $0.28 | ||
| Claude Opus 4.6 | ServiceX + Awkward Array + Hist · Historical import · legacy-d63e64dde22b | 73.9% | $0.28 | ||
| ServiceX + Awkward Array + Hist · Combined current + historical contexts | 73.3% | $0.04 | |||
| ServiceX + Awkward Array + Hist · Historical import · legacy-d63e64dde22b | 73.3% | $0.04 | |||
| Kimi K2.5 | ServiceX + ROOT RDataFrame · Combined recorded contexts | 72% | $0.05 | ||
| Kimi K2.5 | ServiceX + ROOT RDataFrame · Historical import · legacy-b55696a333ff | 72% | $0.05 | ||
| ServiceX + Awkward Array + Hist · Combined current + historical contexts | 65% | $0.05 | |||
| ServiceX + Awkward Array + Hist · Historical import · legacy-d63e64dde22b | 65% | $0.05 | |||
| gpt-oss-120b | ServiceX + Awkward Array + Hist · Combined current + historical contexts | 60.6% | $0.03 | ||
| gpt-oss-120b | ServiceX + Awkward Array + Hist · Historical import · legacy-d63e64dde22b | 60.6% | $0.03 | ||
| grok-code-fast-1 | ServiceX + Awkward Array + Hist · Combined current + historical contexts | 60.6% | $0.06 | ||
| grok-code-fast-1 | ServiceX + Awkward Array + Hist · Historical import · legacy-d63e64dde22b | 60.6% | $0.06 | ||
| ServiceX + Awkward Array + Hist · Combined current + historical contexts | 53.9% | $0.04 | |||
| ServiceX + Awkward Array + Hist · Historical import · legacy-d63e64dde22b | 53.9% | $0.04 | |||
| gpt-oss-20b | ServiceX + Awkward Array + Hist · Combined current + historical contexts | 45% | $0.02 | ||
| gpt-oss-20b | ServiceX + Awkward Array + Hist · Historical import · legacy-d63e64dde22b | 45% | $0.02 | ||
| ServiceX + Awkward Array + Hist · Combined current + historical contexts | 25% | $0.03 | |||
| ServiceX + Awkward Array + Hist · Historical import · legacy-d63e64dde22b | 25% | $0.03 |
3 models have held number one on the official leaderboard since its release in September 2025
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official LLM Physics Plotting Benchmark leaderboard
GPT-5 mini on the official leaderboard passed 85% in August 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.
Source: Official LLM Physics Plotting Benchmark 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
- 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 9 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
- Pass Independent runs Scores from the official leaderboard (19 entries).
- Pass Models scored 17 models we track, plus 2 other entries on its leaderboard.
- Pass Newest score The newest is from July 2026, for GPT-5.6 Luna.
- 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 90.6%, past 85% since August 2025.
Leaderboard import 3 pass
- Pass Importer We read the board on gordonwatts.github.io: 44 rows for models we track and 2 other entries 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.