Model comparison
Mistral Large vs Qwen3.5-Flash
Qwen3.5-Flash is the stronger model overall, scoring 42.5 to 31.9 on the Noometry Index.
Last verified . 25 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 25 benchmarks with published results for both. Mistral Large scores higher in 1 category and Qwen3.5-Flash in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.5-Flash leads 37.4 to 18.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 8.5% for Mistral Large and 84.4% for Qwen3.5-Flash.
- Qwen3.5-Flash is cheaper at $0.10 / $0.40 per million input/output tokens, against $2 / $6 for Mistral Large.
- Qwen3.5-Flash accepts more context: 1M tokens versus 131K.
- Mistral Large has downloadable open weights; the other is API-only.
Side by side
| Mistral Large | Qwen3.5-Flash | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 31.9 | 42.5 |
| Released | 2024-02-26 | 2026-02-23 |
| Weights | Open | Proprietary |
| Context window | 131K | 1M |
| Max output | 16K | 66K |
| Input $ / M tokens | $2 | $0.10 |
| Output $ / M tokens | $6 | $0.40 |
| Results tracked | 51 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Mistral Large: 34.3 (#240), Qwen3.5-Flash: 34.2 (#242)
| Benchmark | Mistral Large | Qwen3.5-Flash |
|---|---|---|
| LMArena Coding | 1277 | 1412 |
| ALE-Bench | 264.7 | 221.8 |
| LMArena WebDev | — | 1244 |
| SciCode | 36.2% | — |
| BigCodeBench Instruct | 30% | — |
| LiveBench Coding | 47.1% | — |
| BigCodeBench Complete | 38.3% | — |
| HumanEval+ | 62.2% | — |
| MBPP+ | 59.5% | — |
Agentic & Tool Use Not comparable
Mistral Large: 28.6 (#89), Qwen3.5-Flash: —
| Benchmark | Mistral Large | Qwen3.5-Flash |
|---|---|---|
| Berkeley Function Calling Leaderboard | 38.4% | — |
| Vending-Bench 2 | — | 462.69 |
Reasoning Qwen3.5-Flash leads
Mistral Large: 15.8 (#310), Qwen3.5-Flash: 33.7 (#72)
| Benchmark | Mistral Large | Qwen3.5-Flash |
|---|---|---|
| LMArena Hard Prompts | 1257 | 1403 |
| DTBench | 65.1% | 82.9% |
| LMCA | 16.7% | 29.1% |
| Epoch Capabilities Index | 128.52 | 143.98 |
| SimpleBench | 22.5% | — |
| CritPt | 0% | — |
| Chess Puzzles | — | 21% |
| LiveBench Reasoning | 43.5% | — |
| Mystery Game Puzzles | — | 20% |
| LiveBench Data Analysis | 50.1% | — |
| ForecastBench | 57.1 | — |
| LiveBench | 48.4% | — |
Math Qwen3.5-Flash leads
Mistral Large: 18.2 (#291), Qwen3.5-Flash: 37.4 (#158)
| Benchmark | Mistral Large | Qwen3.5-Flash |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | 84.4% |
| LMArena Math | 1262 | 1407 |
| FrontierMath (Feb 2025 set) | 0.3% | 6.2% |
| FrontierMath (Tiers 1-3) | — | 18.2% |
| Omni-MATH | 28.1% | — |
| LiveBench Math | 42.5% | — |
| MATH Level 5 | 50.3% | — |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Qwen3.5-Flash leads
Mistral Large: 30.1 (#230), Qwen3.5-Flash: 43.2 (#93)
| Benchmark | Mistral Large | Qwen3.5-Flash |
|---|---|---|
| GPQA Diamond | 51.3% | 82.3% |
| Vectara Hallucination Rate | 4.5% | 10.5% |
| LMArena Expert | 1232 | 1407 |
| SimpleQA Verified | — | 20.3% |
| MMLU-Pro | 59.9% | — |
| Confabulations | 21.4% | — |
| GPQA (HELM) | 43.5% | — |
| MMLU | 80% | — |
Multilingual Qwen3.5-Flash leads
Mistral Large: 40.0 (#219), Qwen3.5-Flash: 50.5 (#121)
| Benchmark | Mistral Large | Qwen3.5-Flash |
|---|---|---|
| LMArena Non-English | 1237 | 1385 |
| LMArena Chinese | 1240 | 1446 |
| LMArena French | 1325 | 1412 |
| LMArena German | 1254 | 1390 |
| LMArena Japanese | 1188 | 1368 |
| LMArena Korean | 1202 | 1344 |
| LMArena Russian | 1257 | 1379 |
| LMArena Spanish | 1268 | 1400 |
Instruction Following Qwen3.5-Flash leads
Mistral Large: 67.9 (#191), Qwen3.5-Flash: 72.6 (#139)
| Benchmark | Mistral Large | Qwen3.5-Flash |
|---|---|---|
| LMArena Instruction Following | 1249 | 1374 |
| LiveBench Instruction Following | 67.9% | — |
| IFEval | 87.7% | — |
Long Context Qwen3.5-Flash leads
Mistral Large: 38.3 (#199), Qwen3.5-Flash: 42.4 (#124)
| Benchmark | Mistral Large | Qwen3.5-Flash |
|---|---|---|
| LMArena Longer Query | 1261 | 1392 |
Writing & Preference Qwen3.5-Flash leads
Mistral Large: 40.7 (#242), Qwen3.5-Flash: 57.9 (#122)
| Benchmark | Mistral Large | Qwen3.5-Flash |
|---|---|---|
| LMArena Text | 1266 | 1397 |
| LMArena Creative Writing | 1243 | 1343 |
| LMArena Multi-Turn | 1260 | 1393 |
| Short-Story Creative Writing | 69% | — |
| EQ-Bench Creative Writing | 985 | — |
| WildBench | 80.1% | — |
| LiveBench Language | 39.4% | — |
Frequently asked questions
Is Mistral Large better than Qwen3.5-Flash?
Qwen3.5-Flash is the stronger model overall, scoring 42.5 to 31.9 on the Noometry Index.
Which is cheaper, Mistral Large or Qwen3.5-Flash?
Qwen3.5-Flash is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; Mistral Large lists at $2 and $6.
Is Mistral Large or Qwen3.5-Flash better for coding?
They score almost the same on coding (34.3 vs 34.2); test both on your own repository before choosing.
Which has the bigger context window?
Qwen3.5-Flash does, with 1M tokens against 131K.
How many benchmarks do Mistral Large and Qwen3.5-Flash share?
25 benchmarks have published results for both models. Mistral Large has 51 scored results on Noometry and Qwen3.5-Flash has 32.