Noometry

Model comparison

Claude 3 Opus vs Mistral Nemo

Claude 3 Opus is the stronger model overall, scoring 29.5 to 26.4 on the Noometry Index.

Last verified . 4 shared benchmarks.

Claude 3 Opus Anthropic

29.5

Rank #310 Confirmed

Mistral Nemo Mistral AI

26.4

Rank #337 Confirmed

Summary

  • They share 4 benchmarks with published results for both. Claude 3 Opus scores higher in 3 categories and Mistral Nemo in 2 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Claude 3 Opus leads 47.2 to 28.5.
  • The biggest single-benchmark swing is MATH Level 5: 37.5% for Claude 3 Opus and 10.8% for Mistral Nemo.
  • Mistral Nemo has downloadable open weights; the other is API-only.

Side by side

Claude 3 OpusMistral Nemo
ProviderAnthropicMistral AI
Noometry Index29.526.4
Released2024-02-292024-07-01
WeightsProprietaryOpen
Context window—128K
Max output—128K
Input $ / M tokens—$0.15
Output $ / M tokens—$0.15
Results tracked4610

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Not comparable

Claude 3 Opus: 32.9 (#267), Mistral Nemo: —

BenchmarkClaude 3 OpusMistral Nemo
WeirdML19.2%—
BigCodeBench Instruct45.5%—
LiveBench Coding38.6%—
LMArena Coding1264—
BigCodeBench Complete57.4%—
HumanEval+77.4%—
MBPP+73.3%—

Agentic & Tool Use Claude 3 Opus leads

Claude 3 Opus: 24.6 (#116), Mistral Nemo: 23.5 (#125)

BenchmarkClaude 3 OpusMistral Nemo
Berkeley Function Calling Leaderboard—27.6%
Cybench10%—
BALROG—17.6%
METR Time Horizons29.5%—

Reasoning Mistral Nemo leads

Claude 3 Opus: 14.6 (#324), Mistral Nemo: 20.7 (#232)

BenchmarkClaude 3 OpusMistral Nemo
DTBench61.6%48.6%
Epoch Capabilities Index126.91118.68
SimpleBench23.5%—
Chess Puzzles5%—
EnigmaEval0.8%—
LiveBench Reasoning40.6%—
LMArena Hard Prompts1245—
LiveBench Data Analysis57.9%—
LMCA17%—
ForecastBench58.4—
LiveBench49.2%—
PIQA—83.5%
WinoGrande88.5%—

Math Mistral Nemo leads

Claude 3 Opus: 14.8 (#299), Mistral Nemo: 25.5 (#268)

BenchmarkClaude 3 OpusMistral Nemo
MATH Level 537.5%10.8%
OTIS Mock AIME 2024-20254.7%—
LiveBench Math43.6%—
LMArena Math1273—
GSM8K—84.2%

Knowledge Claude 3 Opus leads

Claude 3 Opus: 24.5 (#267), Mistral Nemo: 12.3 (#298)

BenchmarkClaude 3 OpusMistral Nemo
GPQA Diamond47.2%29.9%
SimpleQA Verified12.6%—
Confabulations22.7%—
LMArena Expert1223—
BoolQ—82.5%
MMLU84.6%—

Multimodal Not comparable

Claude 3 Opus: 27.1 (#116), Mistral Nemo: —

BenchmarkClaude 3 OpusMistral Nemo
LMArena Vision1023—

Multilingual Not comparable

Claude 3 Opus: 41.4 (#207), Mistral Nemo: —

BenchmarkClaude 3 OpusMistral Nemo
LMArena Non-English1258—
LMArena Chinese1248—
LMArena French1275—
LMArena German1258—
LMArena Japanese1204—
LMArena Korean1187—
LMArena Russian1280—
LMArena Spanish1246—

Instruction Following Not comparable

Claude 3 Opus: 64.1 (#228), Mistral Nemo: —

BenchmarkClaude 3 OpusMistral Nemo
LiveBench Instruction Following63.9%—
LMArena Instruction Following1248—

Long Context Not comparable

Claude 3 Opus: 38.2 (#202), Mistral Nemo: —

BenchmarkClaude 3 OpusMistral Nemo
LMArena Longer Query1259—

Writing & Preference Claude 3 Opus leads

Claude 3 Opus: 47.2 (#213), Mistral Nemo: 28.5 (#296)

BenchmarkClaude 3 OpusMistral Nemo
LMArena Text1262—
LMArena Creative Writing1235—
EQ-Bench Creative Writing—881
LMArena Multi-Turn1275—
LiveBench Language50.4%—

Frequently asked questions

Is Claude 3 Opus better than Mistral Nemo?

Claude 3 Opus is the stronger model overall, scoring 29.5 to 26.4 on the Noometry Index.

How many benchmarks do Claude 3 Opus and Mistral Nemo share?

4 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and Mistral Nemo has 10.

Related comparisons

Go deeper