Skip to content

Benchmark

ChemBench Analytical Chemistry

Science benchmarks measure how well models answer science questions. Higher scores are better.

Models measured
42
Scores recorded
51
Sources
1
IQ weight
1.64

Score distribution

0.451
Mean
0.428
Median
0.171
Std dev
0.27
10th percentile
0.651
90th percentile
0.00658
Min
0.006580.816
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.64 for chat models, measured over 42 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Claude Opus 4.7claude-opus-4-7-tinyeval· ChemBench verified leaderboard data docs0.816
2Claude Opus 4.8claude-opus-4-8-tinyeval· ChemBench verified leaderboard data docs0.809
3GPT-5 nanoGPT-5-nano-base-1764459351· ChemBench verified leaderboard data docs0.743
4Claude Opus 4.5claude-opus-4-5-tinyeval· ChemBench verified leaderboard data docs0.691
5DeepSeek V3.2deepseek-v3-2-tinyeval· ChemBench verified leaderboard data docs0.658
6Kimi K2.5kimi-k2-5-tinyeval· ChemBench verified leaderboard data docs0.651
7O1 Previewo1-preview· ChemBench verified leaderboard data docs0.625
8gemini-2.5-flash-preview-04-17gemini-2.5-flash-preview-04-17-base-1750491557· ChemBench verified leaderboard data docs0.618
9GPT OSS 120Bgpt-oss-120b-base-1760293341· ChemBench verified leaderboard data docs0.618
10Claude 3.5 Sonnetclaude3.5-react· ChemBench verified leaderboard data docs0.579
11DeepSeek R1deepseek-r1-tinyeval· ChemBench verified leaderboard data docs0.579
12Kimi K2 Instructkimi-k2-instruct-0905-base-1760364223· ChemBench verified leaderboard data docs0.579
13Claude 3.5 Sonnetclaude3.5· ChemBench verified leaderboard data docs0.566
14GLM 5glm-5-tinyeval· ChemBench verified leaderboard data docs0.566
15GPT 4ogpt-4o· ChemBench verified leaderboard data docs0.559
16Qwen3 235B A22B Instruct 2507qwen3-235b-a22b-2507-tinyeval· ChemBench verified leaderboard data docs0.553
17Nemotron Super 3 120bnemotron-super-3-120b-tinyeval· ChemBench verified leaderboard data docs0.546
18Llama 4 Maverickgroq_meta-llama/llama-4-maverick-17b-128e-instruct_e8a077d8· ChemBench verified leaderboard data docs0.533
19Qwen3 Next 80B A3Bqwen3-next-80b-a3b-tinyeval· ChemBench verified leaderboard data docs0.533
20GPT OSS 20bgpt-oss-20b-base-1760359009· ChemBench verified leaderboard data docs0.52
21Llama 3.1 405B Instructllama3.1-405b-instruct· ChemBench verified leaderboard data docs0.507
22MiniMax M2.5minimax-m2-5-tinyeval· ChemBench verified leaderboard data docs0.493
23Mistral Large 2mistral-large-2-123b· ChemBench verified leaderboard data docs0.48
24GPT 4ogpt-4o-react· ChemBench verified leaderboard data docs0.467
25GPT 4gpt-4· ChemBench verified leaderboard data docs0.428
26Qwen2.5 32BQwen-2.5-32B-base-1740920072· ChemBench verified leaderboard data docs0.428
27Claude 3 Haikuclaude-3-haiku-tinyeval· ChemBench verified leaderboard data docs0.421
28Llama 3 70B Instructllama3-70b-instruct· ChemBench verified leaderboard data docs0.414
29Llama 3 8B Instructllama3-8b-instruct· ChemBench verified leaderboard data docs0.408
30Llama 3.1 70B Instructllama3.1-70b-instruct· ChemBench verified leaderboard data docs0.408
31Llama 3 8B Instructllama3-8b-instruct-T-one· ChemBench verified leaderboard data docs0.401
32Llama 3.1 8B Instructllama3.1-8b-instruct· ChemBench verified leaderboard data docs0.395
33Gemini Progemini-pro· ChemBench verified leaderboard data docs0.388
34GPT-3.5 Turbogpt-3.5-turbo· ChemBench verified leaderboard data docs0.382
35Claude 2claude2· ChemBench verified leaderboard data docs0.375
36GPT-4o miniGPT-4o-mini-base-1764283510· ChemBench verified leaderboard data docs0.375
37Llama 3 70B Instructllama3-70b-instruct-T-one· ChemBench verified leaderboard data docs0.375
38Llama 3.1 70B Instructllama3.1-70b-instruct-T-one· ChemBench verified leaderboard data docs0.368
39Llama 3.1 8B Instructllama3.1-8b-instruct-T-one· ChemBench verified leaderboard data docs0.362
40Command R Pluscommand-r+· ChemBench verified leaderboard data docs0.342
41Phi-3 Medium 4K Instructphi-3-medium-4k-instruct· ChemBench verified leaderboard data docs0.342
42Nemotron Nano 3 30Bnemotron-nano-3-30b-tinyeval· ChemBench verified leaderboard data docs0.336
43Gemma 2 9B ITgemma-2-9b-it· ChemBench verified leaderboard data docs0.316
44Gemma 2 9B ITgemma-2-9b-it-T-one· ChemBench verified leaderboard data docs0.289
45Mixtral 8x7B Instructmixtral-8x7b-instruct-T-one· ChemBench verified leaderboard data docs0.276
46Mixtral 8x7B Instructmixtral-8x7b-instruct· ChemBench verified leaderboard data docs0.27
47Gemma 1.1 7B ITgemma-1-1-7b-it· ChemBench verified leaderboard data docs0.211
48Gemma 1.1 7B ITgemma-1-1-7b-it-T-one· ChemBench verified leaderboard data docs0.211
49Llama 2 13B Chatllama2-13b-chat· ChemBench verified leaderboard data docs0.0921
50Llama 2 70B Chatllama2-70b-chat· ChemBench verified leaderboard data docs0.0724

Showing 1–50 of 51 results.

Data credits: ChemBench leaderboard, Jablonka group / lamalab-org. Public verified numeric result summaries; results licence not separately stated.