Model comparison
Mistral Small vs Qwen3.5 122B-A10B
Qwen3.5 122B-A10B is the stronger model overall, scoring 41.6 to 33.1 on the Noometry Index. Mistral Small costs 4.2× less per token, which makes it the better buy when Qwen3.5 122B-A10B's lead doesn't matter for your workload.
Last verified . 23 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 23 benchmarks with published results for both. Mistral Small scores higher in 0 categories and Qwen3.5 122B-A10B in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.5 122B-A10B leads 36.4 to 15.4.
- The biggest single-benchmark swing is DTBench: 70.9% for Mistral Small and 84.3% for Qwen3.5 122B-A10B.
- Mistral Small is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.40 / $3.20 for Qwen3.5 122B-A10B.
- Qwen3.5 122B-A10B accepts more context: 262K tokens versus 256K.
Side by side
| Mistral Small | Qwen3.5 122B-A10B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 33.1 | 41.6 |
| Released | 2024-02-26 | 2026-02-23 |
| Weights | Open | Open |
| Context window | 256K | 262K |
| Max output | 256K | 66K |
| Input $ / M tokens | $0.15 | $0.40 |
| Output $ / M tokens | $0.60 | $3.20 |
| Results tracked | 39 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.5 122B-A10B leads
Mistral Small: 33.5 (#242), Qwen3.5 122B-A10B: 38.8 (#155)
| Benchmark | Mistral Small | Qwen3.5 122B-A10B |
|---|---|---|
| SciCode | 26.5% | 35.6% |
| LMArena Coding | 1363 | 1436 |
| LMArena WebDev | — | 1360 |
| BigCodeBench Instruct | 36.1% | — |
| LiveBench Coding | 36.2% | — |
| BigCodeBench Complete | 46.6% | — |
| ALE-Bench | 497.62 | — |
Agentic & Tool Use Not comparable
Mistral Small: 27.9 (#87), Qwen3.5 122B-A10B: —
| Benchmark | Mistral Small | Qwen3.5 122B-A10B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.1% | — |
Reasoning Qwen3.5 122B-A10B leads
Mistral Small: 19.3 (#238), Qwen3.5 122B-A10B: 26.4 (#121)
| Benchmark | Mistral Small | Qwen3.5 122B-A10B |
|---|---|---|
| CritPt | 0% | 0.9% |
| LMArena Hard Prompts | 1336 | 1421 |
| DTBench | 70.9% | 84.3% |
| LMCA | 20.6% | 32.2% |
| Kagi LLM Benchmark | 37.8% | — |
| NYT Connections (extended) | — | 51.7% |
| Thematic Generalization | — | 51.2% |
| LiveBench Reasoning | 44.8% | — |
| Mystery Game Puzzles | — | 17% |
| LiveBench Data Analysis | 53.7% | — |
| LiveBench | 44% | — |
Math Qwen3.5 122B-A10B leads
Mistral Small: 15.4 (#287), Qwen3.5 122B-A10B: 36.4 (#114)
| Benchmark | Mistral Small | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Math | 1341 | 1432 |
| OTIS Mock AIME 2024-2025 | 5.8% | — |
| LiveBench Math | 39.9% | — |
| MATH Level 5 | 46.8% | — |
Knowledge Qwen3.5 122B-A10B leads
Mistral Small: 30.9 (#214), Qwen3.5 122B-A10B: 38.2 (#138)
| Benchmark | Mistral Small | Qwen3.5 122B-A10B |
|---|---|---|
| Vectara Hallucination Rate | 5.1% | 11.2% |
| LMArena Expert | 1293 | 1431 |
| GPQA Diamond | 47.5% | — |
| MMLU | 68.7% | — |
Multimodal Qwen3.5 122B-A10B leads
Mistral Small: 32.9 (#91), Qwen3.5 122B-A10B: 39.0 (#52)
| Benchmark | Mistral Small | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Vision | 1142 | 1245 |
Multilingual Qwen3.5 122B-A10B leads
Mistral Small: 45.7 (#164), Qwen3.5 122B-A10B: 51.8 (#101)
| Benchmark | Mistral Small | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Non-English | 1315 | 1400 |
| LMArena Chinese | 1342 | 1462 |
| LMArena French | 1337 | 1442 |
| LMArena German | 1341 | 1425 |
| LMArena Japanese | 1275 | 1364 |
| LMArena Korean | 1260 | 1353 |
| LMArena Russian | 1324 | 1400 |
| LMArena Spanish | 1346 | 1423 |
Instruction Following Qwen3.5 122B-A10B leads
Mistral Small: 66.6 (#204), Qwen3.5 122B-A10B: 74.0 (#109)
| Benchmark | Mistral Small | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Instruction Following | 1310 | 1399 |
| LiveBench Instruction Following | 63.7% | — |
Long Context Qwen3.5 122B-A10B leads
Mistral Small: 40.4 (#151), Qwen3.5 122B-A10B: 43.0 (#105)
| Benchmark | Mistral Small | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Longer Query | 1327 | 1410 |
Writing & Preference Qwen3.5 122B-A10B leads
Mistral Small: 52.6 (#165), Qwen3.5 122B-A10B: 60.2 (#98)
| Benchmark | Mistral Small | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Text | 1338 | 1417 |
| LMArena Creative Writing | 1304 | 1369 |
| LMArena Multi-Turn | 1344 | 1416 |
| LiveBench Language | 30.5% | — |
Frequently asked questions
Is Mistral Small better than Qwen3.5 122B-A10B?
Qwen3.5 122B-A10B is the stronger model overall, scoring 41.6 to 33.1 on the Noometry Index. Mistral Small costs 4.2× less per token, which makes it the better buy when Qwen3.5 122B-A10B's lead doesn't matter for your workload.
Which is cheaper, Mistral Small or Qwen3.5 122B-A10B?
Mistral Small is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Qwen3.5 122B-A10B lists at $0.40 and $3.20.
Is Mistral Small or Qwen3.5 122B-A10B better for coding?
Qwen3.5 122B-A10B scores higher on coding benchmarks: 38.8 versus 33.5 in the Noometry coding category.
Which has the bigger context window?
Qwen3.5 122B-A10B does, with 262K tokens against 256K.
How many benchmarks do Mistral Small and Qwen3.5 122B-A10B share?
23 benchmarks have published results for both models. Mistral Small has 39 scored results on Noometry and Qwen3.5 122B-A10B has 27.