Noometry

Model comparison

Claude 3 Opus vs Ministral 8B

Claude 3 Opus is the stronger model overall, scoring 29.5 to 28.2 on the Noometry Index.

Last verified . 15 shared benchmarks.

Claude 3 Opus Anthropic

29.5

Rank #310 Confirmed

Ministral 8B Mistral AI

28.2

Rank #325 Confirmed

Summary

  • They share 15 benchmarks with published results for both. Claude 3 Opus scores higher in 6 categories and Ministral 8B in 3 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Claude 3 Opus leads 24.5 to 12.6.
  • The biggest single-benchmark swing is MATH Level 5: 37.5% for Claude 3 Opus and 14.9% for Ministral 8B.
  • Ministral 8B has downloadable open weights; the other is API-only.

Side by side

Claude 3 OpusMinistral 8B
ProviderAnthropicMistral AI
Noometry Index29.528.2
Released2024-02-292024-10-01
WeightsProprietaryOpen
Context window—262K
Max output—262K
Input $ / M tokens—$0.15
Output $ / M tokens—$0.15
Results tracked4617

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

Category by category

Coding Ministral 8B leads

Claude 3 Opus: 32.9 (#267), Ministral 8B: 35.0 (#230)

BenchmarkClaude 3 OpusMinistral 8B
LMArena Coding12641202
WeirdML19.2%—
BigCodeBench Instruct45.5%—
LiveBench Coding38.6%—
BigCodeBench Complete57.4%—
HumanEval+77.4%—
MBPP+73.3%—

Agentic & Tool Use Claude 3 Opus leads

Claude 3 Opus: 24.6 (#116), Ministral 8B: 16.4 (#148)

BenchmarkClaude 3 OpusMinistral 8B
Berkeley Function Calling Leaderboard—11.1%
Cybench10%—
METR Time Horizons29.5%—

Reasoning Ministral 8B leads

Claude 3 Opus: 14.6 (#324), Ministral 8B: 18.4 (#281)

BenchmarkClaude 3 OpusMinistral 8B
LMArena Hard Prompts12451191
DTBench61.6%45.7%
SimpleBench23.5%—
Chess Puzzles5%—
EnigmaEval0.8%—
LiveBench Reasoning40.6%—
LiveBench Data Analysis57.9%—
LMCA17%—
Epoch Capabilities Index126.91—
ForecastBench58.4—
LiveBench49.2%—
WinoGrande88.5%—

Math Ministral 8B leads

Claude 3 Opus: 14.8 (#299), Ministral 8B: 25.7 (#267)

BenchmarkClaude 3 OpusMinistral 8B
LMArena Math12731188
MATH Level 537.5%14.9%
OTIS Mock AIME 2024-20254.7%—
LiveBench Math43.6%—

Knowledge Claude 3 Opus leads

Claude 3 Opus: 24.5 (#267), Ministral 8B: 12.6 (#297)

BenchmarkClaude 3 OpusMinistral 8B
GPQA Diamond47.2%27.1%
LMArena Expert12231170
SimpleQA Verified12.6%—
Confabulations22.7%—
Vectara Hallucination Rate—7.4%
MMLU84.6%—

Multimodal Not comparable

Claude 3 Opus: 27.1 (#116), Ministral 8B: —

BenchmarkClaude 3 OpusMinistral 8B
LMArena Vision1023—

Multilingual Claude 3 Opus leads

Claude 3 Opus: 41.4 (#207), Ministral 8B: 35.1 (#247)

BenchmarkClaude 3 OpusMinistral 8B
LMArena Non-English12581165
LMArena Chinese12481193
LMArena Russian12801195
LMArena French1275—
LMArena German1258—
LMArena Japanese1204—
LMArena Korean1187—
LMArena Spanish1246—

Instruction Following Claude 3 Opus leads

Claude 3 Opus: 64.1 (#228), Ministral 8B: 60.5 (#250)

BenchmarkClaude 3 OpusMinistral 8B
LMArena Instruction Following12481161
LiveBench Instruction Following63.9%—

Long Context Claude 3 Opus leads

Claude 3 Opus: 38.2 (#202), Ministral 8B: 36.7 (#227)

BenchmarkClaude 3 OpusMinistral 8B
LMArena Longer Query12591212

Writing & Preference Claude 3 Opus leads

Claude 3 Opus: 47.2 (#213), Ministral 8B: 39.6 (#246)

BenchmarkClaude 3 OpusMinistral 8B
LMArena Text12621191
LMArena Creative Writing12351175
LMArena Multi-Turn12751166
LiveBench Language50.4%—

Frequently asked questions

Is Claude 3 Opus better than Ministral 8B?

Claude 3 Opus is the stronger model overall, scoring 29.5 to 28.2 on the Noometry Index.

Is Claude 3 Opus or Ministral 8B better for coding?

Ministral 8B scores higher on coding benchmarks: 35.0 versus 32.9 in the Noometry coding category.

How many benchmarks do Claude 3 Opus and Ministral 8B share?

15 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and Ministral 8B has 17.

Related comparisons

Go deeper