Model comparison
Mistral Small 3 vs Qwen2.5 7B Instruct
Mistral Small 3 is the stronger model overall, scoring 31.2 to 29.0 on the Noometry Index.
Last verified . 6 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 6 benchmarks with published results for both. Mistral Small 3 scores higher in 5 categories and Qwen2.5 7B Instruct in 1 category; 4 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen2.5 7B Instruct leads 48.8 to 32.2.
- The biggest single-benchmark swing is GPQA Diamond: 47.3% for Mistral Small 3 and 35.5% for Qwen2.5 7B Instruct.
- Mistral Small 3 is cheaper at $0.05 / $0.08 per million input/output tokens, against $0.17 / $0.70 for Qwen2.5 7B Instruct.
- Qwen2.5 7B Instruct accepts more context: 131K tokens versus 33K.
Side by side
| Mistral Small 3 | Qwen2.5 7B Instruct | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 31.2 | 29.0 |
| Released | 2025-01-30 | 2024-09 |
| Weights | Open | Open |
| Context window | 33K | 131K |
| Max output | 16K | 8K |
| Input $ / M tokens | $0.05 | $0.17 |
| Output $ / M tokens | $0.08 | $0.70 |
| Results tracked | 24 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Mistral Small 3: 36.5 (#207), Qwen2.5 7B Instruct: 36.5 (#208)
| Benchmark | Mistral Small 3 | Qwen2.5 7B Instruct |
|---|---|---|
| BigCodeBench Instruct | 45.3% | 37.6% |
| BigCodeBench Complete | 50.4% | 46.1% |
| LMArena Coding | 1246 | — |
Agentic & Tool Use Not comparable
Mistral Small 3: —, Qwen2.5 7B Instruct: 23.8 (#124)
| Benchmark | Mistral Small 3 | Qwen2.5 7B Instruct |
|---|---|---|
| BALROG | — | 7.8% |
Reasoning Mistral Small 3 leads
Mistral Small 3: 18.9 (#273), Qwen2.5 7B Instruct: 14.8 (#322)
| Benchmark | Mistral Small 3 | Qwen2.5 7B Instruct |
|---|---|---|
| Chess Puzzles | 0% | 0% |
| Epoch Capabilities Index | 127.07 | 118.51 |
| LMArena Hard Prompts | 1233 | — |
| DTBench | — | 47.7% |
| LMCA | — | 6.4% |
Math Mistral Small 3 leads
Mistral Small 3: 16.3 (#295), Qwen2.5 7B Instruct: 12.6 (#306)
| Benchmark | Mistral Small 3 | Qwen2.5 7B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 6.7% | 2.5% |
| Omni-MATH | — | 29.4% |
| LMArena Math | 1240 | — |
Knowledge Mistral Small 3 leads
Mistral Small 3: 25.1 (#263), Qwen2.5 7B Instruct: 17.0 (#286)
| Benchmark | Mistral Small 3 | Qwen2.5 7B Instruct |
|---|---|---|
| GPQA Diamond | 47.3% | 35.5% |
| MMLU-Pro | — | 53.9% |
| Confabulations | 25.2% | — |
| GPQA (HELM) | — | 34.1% |
| LMArena Expert | 1202 | — |
| MMLU | — | 72.9% |
Multilingual Not comparable
Mistral Small 3: 37.3 (#236), Qwen2.5 7B Instruct: —
| Benchmark | Mistral Small 3 | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Non-English | 1198 | — |
| LMArena Chinese | 1204 | — |
| LMArena French | 1203 | — |
| LMArena German | 1211 | — |
| LMArena Japanese | 1111 | — |
| LMArena Korean | 1188 | — |
| LMArena Russian | 1216 | — |
Instruction Following Too close to call
Mistral Small 3: 63.7 (#229), Qwen2.5 7B Instruct: 63.2 (#231)
| Benchmark | Mistral Small 3 | Qwen2.5 7B Instruct |
|---|---|---|
| IFEval | — | 74.1% |
| LMArena Instruction Following | 1214 | — |
Long Context Not comparable
Mistral Small 3: 37.8 (#211), Qwen2.5 7B Instruct: —
| Benchmark | Mistral Small 3 | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Longer Query | 1246 | — |
Writing & Preference Qwen2.5 7B Instruct leads
Mistral Small 3: 32.2 (#280), Qwen2.5 7B Instruct: 48.8 (#195)
| Benchmark | Mistral Small 3 | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Text | 1234 | — |
| LMArena Creative Writing | 1195 | — |
| EQ-Bench Creative Writing | 707 | — |
| WildBench | — | 73.1% |
| LMArena Multi-Turn | 1217 | — |
Frequently asked questions
Is Mistral Small 3 better than Qwen2.5 7B Instruct?
Mistral Small 3 is the stronger model overall, scoring 31.2 to 29.0 on the Noometry Index.
Which is cheaper, Mistral Small 3 or Qwen2.5 7B Instruct?
Mistral Small 3 is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Qwen2.5 7B Instruct lists at $0.17 and $0.70.
Is Mistral Small 3 or Qwen2.5 7B Instruct better for coding?
They score almost the same on coding (36.5 vs 36.5); test both on your own repository before choosing.
Which has the bigger context window?
Qwen2.5 7B Instruct does, with 131K tokens against 33K.
How many benchmarks do Mistral Small 3 and Qwen2.5 7B Instruct share?
6 benchmarks have published results for both models. Mistral Small 3 has 24 scored results on Noometry and Qwen2.5 7B Instruct has 15.