Model comparison
Mistral Large 3 vs Qwen2.5 7B Instruct
Mistral Large 3 is the stronger model overall, scoring 39.1 to 29.0 on the Noometry Index.
Last verified . 0 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- The widest gap is in math, where Mistral Large 3 leads 38.7 to 12.6.
- Qwen2.5 7B Instruct is cheaper at $0.17 / $0.70 per million input/output tokens, against $0.25 / $0.75 for Mistral Large 3.
- Mistral Large 3 accepts more context: 262K tokens versus 131K.
Side by side
| Mistral Large 3 | Qwen2.5 7B Instruct | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 39.1 | 29.0 |
| Released | 2025-12-02 | 2024-09 |
| Weights | Open | Open |
| Context window | 262K | 131K |
| Max output | 8K | 8K |
| Input $ / M tokens | $0.25 | $0.17 |
| Output $ / M tokens | $0.75 | $0.70 |
| Results tracked | 24 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5 7B Instruct leads
Mistral Large 3: 34.4 (#237), Qwen2.5 7B Instruct: 36.5 (#208)
| Benchmark | Mistral Large 3 | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena WebDev | 1230 | — |
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1448 | — |
| BigCodeBench Complete | — | 46.1% |
Agentic & Tool Use Not comparable
Mistral Large 3: —, Qwen2.5 7B Instruct: 23.8 (#124)
| Benchmark | Mistral Large 3 | Qwen2.5 7B Instruct |
|---|---|---|
| BALROG | — | 7.8% |
Reasoning Too close to call
Mistral Large 3: 15.2 (#319), Qwen2.5 7B Instruct: 14.8 (#322)
| Benchmark | Mistral Large 3 | Qwen2.5 7B Instruct |
|---|---|---|
| Kagi LLM Benchmark | 50.9% | — |
| NYT Connections (extended) | 7.5% | — |
| Chess Puzzles | — | 0% |
| Thematic Generalization | 23% | — |
| LMArena Hard Prompts | 1429 | — |
| DTBench | — | 47.7% |
| LMCA | — | 6.4% |
| Epoch Capabilities Index | — | 118.51 |
Math Mistral Large 3 leads
Mistral Large 3: 38.7 (#129), Qwen2.5 7B Instruct: 12.6 (#306)
| Benchmark | Mistral Large 3 | Qwen2.5 7B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 2.5% |
| Omni-MATH | — | 29.4% |
| LMArena Math | 1414 | — |
Knowledge Mistral Large 3 leads
Mistral Large 3: 36.0 (#177), Qwen2.5 7B Instruct: 17.0 (#286)
| Benchmark | Mistral Large 3 | Qwen2.5 7B Instruct |
|---|---|---|
| GPQA Diamond | — | 35.5% |
| MMLU-Pro | — | 53.9% |
| Vectara Hallucination Rate | 14.5% | — |
| GPQA (HELM) | — | 34.1% |
| LMArena Expert | 1421 | — |
| MMLU | — | 72.9% |
Multimodal Not comparable
Mistral Large 3: 38.2 (#66), Qwen2.5 7B Instruct: —
| Benchmark | Mistral Large 3 | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Vision | 1221 | — |
Multilingual Not comparable
Mistral Large 3: 52.5 (#84), Qwen2.5 7B Instruct: —
| Benchmark | Mistral Large 3 | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Non-English | 1413 | — |
| LMArena Chinese | 1447 | — |
| LMArena French | 1455 | — |
| LMArena German | 1437 | — |
| LMArena Japanese | 1394 | — |
| LMArena Korean | 1384 | — |
| LMArena Russian | 1411 | — |
| LMArena Spanish | 1440 | — |
Instruction Following Mistral Large 3 leads
Mistral Large 3: 74.0 (#108), Qwen2.5 7B Instruct: 63.2 (#231)
| Benchmark | Mistral Large 3 | Qwen2.5 7B Instruct |
|---|---|---|
| IFEval | — | 74.1% |
| LMArena Instruction Following | 1403 | — |
Long Context Not comparable
Mistral Large 3: 43.1 (#105), Qwen2.5 7B Instruct: —
| Benchmark | Mistral Large 3 | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Longer Query | 1413 | — |
Writing & Preference Mistral Large 3 leads
Mistral Large 3: 60.0 (#101), Qwen2.5 7B Instruct: 48.8 (#195)
| Benchmark | Mistral Large 3 | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Text | 1428 | — |
| LMArena Creative Writing | 1386 | — |
| EQ-Bench Creative Writing | 1412 | — |
| WildBench | — | 73.1% |
| LMArena Multi-Turn | 1429 | — |
Frequently asked questions
Is Mistral Large 3 better than Qwen2.5 7B Instruct?
Mistral Large 3 is the stronger model overall, scoring 39.1 to 29.0 on the Noometry Index.
Which is cheaper, Mistral Large 3 or Qwen2.5 7B Instruct?
Qwen2.5 7B Instruct is cheaper. It lists at $0.17 per million input tokens and $0.70 per million output tokens; Mistral Large 3 lists at $0.25 and $0.75.
Is Mistral Large 3 or Qwen2.5 7B Instruct better for coding?
Qwen2.5 7B Instruct scores higher on coding benchmarks: 36.5 versus 34.4 in the Noometry coding category.
Which has the bigger context window?
Mistral Large 3 does, with 262K tokens against 131K.
How many benchmarks do Mistral Large 3 and Qwen2.5 7B Instruct share?
0 benchmarks have published results for both models. Mistral Large 3 has 24 scored results on Noometry and Qwen2.5 7B Instruct has 15.