Noometry

Model comparison

Mistral Small 3 vs Qwen3 8B

Qwen3 8B is the stronger model overall, scoring 33.7 to 31.2 on the Noometry Index. Mistral Small 3 costs 5.4× less per token, which makes it the better buy when Qwen3 8B's lead doesn't matter for your workload.

Last verified . 4 shared benchmarks.

Mistral Small 3 Mistral AI

31.2

Rank #278 Confirmed

Qwen3 8B Alibaba (Qwen)

33.7

Rank #238 Confirmed

Summary

  • They share 4 benchmarks with published results for both. Mistral Small 3 scores higher in 2 categories and Qwen3 8B in 3 categories; 4 gaps are clear of the uncertainty.
  • The widest gap is in math, where Qwen3 8B leads 34.9 to 16.3.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 6.7% for Mistral Small 3 and 56.1% for Qwen3 8B.
  • Mistral Small 3 is cheaper at $0.05 / $0.08 per million input/output tokens, against $0.18 / $0.70 for Qwen3 8B.
  • Qwen3 8B accepts more context: 131K tokens versus 33K.

Side by side

Mistral Small 3Qwen3 8B
ProviderMistral AIAlibaba (Qwen)
Noometry Index31.233.7
Released2025-01-302025-04
WeightsOpenOpen
Context window33K131K
Max output16K8K
Input $ / M tokens$0.05$0.18
Output $ / M tokens$0.08$0.70
Results tracked2411

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

Category by category

Coding Mistral Small 3 leads

Mistral Small 3: 36.5 (#207), Qwen3 8B: 34.0 (#248)

BenchmarkMistral Small 3Qwen3 8B
SciCode—22.6%
BigCodeBench Instruct45.3%—
LMArena Coding1246—
BigCodeBench Complete50.4%—

Agentic & Tool Use Not comparable

Mistral Small 3: —, Qwen3 8B: 30.2 (#78)

BenchmarkMistral Small 3Qwen3 8B
Berkeley Function Calling Leaderboard—42.6%

Reasoning Mistral Small 3 leads

Mistral Small 3: 18.9 (#273), Qwen3 8B: 16.6 (#303)

BenchmarkMistral Small 3Qwen3 8B
Chess Puzzles0%5%
Epoch Capabilities Index127.07136.17
CritPt—0%
LMArena Hard Prompts1233—
DTBench—59.7%
LMCA—8.8%

Math Qwen3 8B leads

Mistral Small 3: 16.3 (#295), Qwen3 8B: 34.9 (#191)

BenchmarkMistral Small 3Qwen3 8B
OTIS Mock AIME 2024-20256.7%56.1%
LMArena Math1240—

Knowledge Qwen3 8B leads

Mistral Small 3: 25.1 (#263), Qwen3 8B: 36.1 (#173)

BenchmarkMistral Small 3Qwen3 8B
GPQA Diamond47.3%56.8%
Confabulations25.2%—
Vectara Hallucination Rate—4.8%
LMArena Expert1202—

Multilingual Not comparable

Mistral Small 3: 37.3 (#236), Qwen3 8B: —

BenchmarkMistral Small 3Qwen3 8B
LMArena Non-English1198—
LMArena Chinese1204—
LMArena French1203—
LMArena German1211—
LMArena Japanese1111—
LMArena Korean1188—
LMArena Russian1216—

Instruction Following Not comparable

Mistral Small 3: 63.7 (#229), Qwen3 8B: —

BenchmarkMistral Small 3Qwen3 8B
LMArena Instruction Following1214—

Long Context Too close to call

Mistral Small 3: 37.8 (#211), Qwen3 8B: 37.9 (#210)

BenchmarkMistral Small 3Qwen3 8B
Fiction.LiveBench—62.1%
LMArena Longer Query1246—

Writing & Preference Not comparable

Mistral Small 3: 32.2 (#280), Qwen3 8B: —

BenchmarkMistral Small 3Qwen3 8B
LMArena Text1234—
LMArena Creative Writing1195—
EQ-Bench Creative Writing707—
LMArena Multi-Turn1217—

Frequently asked questions

Is Mistral Small 3 better than Qwen3 8B?

Qwen3 8B is the stronger model overall, scoring 33.7 to 31.2 on the Noometry Index. Mistral Small 3 costs 5.4× less per token, which makes it the better buy when Qwen3 8B's lead doesn't matter for your workload.

Which is cheaper, Mistral Small 3 or Qwen3 8B?

Mistral Small 3 is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Qwen3 8B lists at $0.18 and $0.70.

Is Mistral Small 3 or Qwen3 8B better for coding?

Mistral Small 3 scores higher on coding benchmarks: 36.5 versus 34.0 in the Noometry coding category.

Which has the bigger context window?

Qwen3 8B does, with 131K tokens against 33K.

How many benchmarks do Mistral Small 3 and Qwen3 8B share?

4 benchmarks have published results for both models. Mistral Small 3 has 24 scored results on Noometry and Qwen3 8B has 11.

Related comparisons

Go deeper