Model comparison
Mistral Small 3 vs Qwen3.8 27B
Qwen3.8 27B is the stronger model overall, scoring 45.3 to 30.9 on the Noometry Index. Mistral Small 3 costs 19× less per token, which makes it the better buy when Qwen3.8 27B's lead doesn't matter for your workload.
Last verified . 18 shared benchmarks.
Mistral AI
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Mistral Small 3 scores higher in 0 categories and Qwen3.8 27B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3.8 27B leads 65.9 to 32.4.
- Mistral Small 3 is cheaper at $0.05 / $0.08 per million input/output tokens, against $0.99 / $1.49 for Qwen3.8 27B.
- Qwen3.8 27B accepts more context: 262K tokens versus 33K.
Side by side
| Mistral Small 3 | Qwen3.8 27B | |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 30.9 | 45.3 |
| Released | 2025-01-30 | 2026-08-14 |
| Weights | Open | Open |
| Context window | 33K | 262K |
| Max output | 16K | 33K |
| Input $ / M tokens | $0.05 | $0.99 |
| Output $ / M tokens | $0.08 | $1.49 |
| Results tracked | 24 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.8 27B leads
Mistral Small 3: 36.0 (#203), Qwen3.8 27B: 50.3 (#42)
| Benchmark | Mistral Small 3 | Qwen3.8 27B |
|---|---|---|
| LMArena Coding | 1246 | 1487 |
| LMArena WebDev | — | 1592 |
| SciCode | — | 46.6% |
| BigCodeBench Instruct | 45.3% | — |
| BigCodeBench Complete | 50.4% | — |
Reasoning Qwen3.8 27B leads
Mistral Small 3: 18.2 (#269), Qwen3.8 27B: 31.5 (#71)
| Benchmark | Mistral Small 3 | Qwen3.8 27B |
|---|---|---|
| LMArena Hard Prompts | 1233 | 1459 |
| Epoch Capabilities Index | 127.06 | 149.38 |
| NYT Connections (extended) | — | 54.5% |
| CritPt | — | 5.4% |
| Chess Puzzles | 0% | — |
| DTBench | — | 88% |
| LMCA | — | 41.4% |
| Surface Evolver Bench | — | 45% |
Math Qwen3.8 27B leads
Mistral Small 3: 15.3 (#290), Qwen3.8 27B: 35.7 (#139)
| Benchmark | Mistral Small 3 | Qwen3.8 27B |
|---|---|---|
| LMArena Math | 1240 | 1453 |
| OTIS Mock AIME 2024-2025 | 6.7% | — |
| ProofBench | — | 16% |
Knowledge Qwen3.8 27B leads
Mistral Small 3: 25.0 (#258), Qwen3.8 27B: 40.9 (#105)
| Benchmark | Mistral Small 3 | Qwen3.8 27B |
|---|---|---|
| LMArena Expert | 1202 | 1482 |
| GPQA Diamond | 47.3% | — |
| Confabulations | 25.2% | — |
Multimodal Not comparable
Mistral Small 3: —, Qwen3.8 27B: 40.5 (#36)
| Benchmark | Mistral Small 3 | Qwen3.8 27B |
|---|---|---|
| LMArena Vision | — | 1270 |
Multilingual Qwen3.8 27B leads
Mistral Small 3: 37.5 (#231), Qwen3.8 27B: 54.0 (#54)
| Benchmark | Mistral Small 3 | Qwen3.8 27B |
|---|---|---|
| LMArena Non-English | 1198 | 1431 |
| LMArena Chinese | 1204 | 1504 |
| LMArena French | 1202 | 1468 |
| LMArena German | 1211 | 1435 |
| LMArena Japanese | 1111 | 1392 |
| LMArena Korean | 1188 | 1389 |
| LMArena Russian | 1216 | 1421 |
| LMArena Spanish | — | 1444 |
Instruction Following Qwen3.8 27B leads
Mistral Small 3: 63.9 (#224), Qwen3.8 27B: 75.8 (#54)
| Benchmark | Mistral Small 3 | Qwen3.8 27B |
|---|---|---|
| LMArena Instruction Following | 1214 | 1436 |
Long Context Qwen3.8 27B leads
Mistral Small 3: 37.8 (#206), Qwen3.8 27B: 44.3 (#66)
| Benchmark | Mistral Small 3 | Qwen3.8 27B |
|---|---|---|
| LMArena Longer Query | 1246 | 1448 |
Writing & Preference Qwen3.8 27B leads
Mistral Small 3: 32.4 (#275), Qwen3.8 27B: 65.9 (#41)
| Benchmark | Mistral Small 3 | Qwen3.8 27B |
|---|---|---|
| LMArena Text | 1234 | 1441 |
| LMArena Creative Writing | 1195 | 1382 |
| EQ-Bench Creative Writing | 707 | 1671 |
| LMArena Multi-Turn | 1217 | 1443 |
Frequently asked questions
Is Mistral Small 3 better than Qwen3.8 27B?
Qwen3.8 27B is the stronger model overall, scoring 45.3 to 30.9 on the Noometry Index. Mistral Small 3 costs 19× less per token, which makes it the better buy when Qwen3.8 27B's lead doesn't matter for your workload.
Which is cheaper, Mistral Small 3 or Qwen3.8 27B?
Mistral Small 3 is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Qwen3.8 27B lists at $0.99 and $1.49.
Is Mistral Small 3 or Qwen3.8 27B better for coding?
Qwen3.8 27B scores higher on coding benchmarks: 50.3 versus 36.0 in the Noometry coding category.
Which has the bigger context window?
Qwen3.8 27B does, with 262K tokens against 33K.
How many benchmarks do Mistral Small 3 and Qwen3.8 27B share?
18 benchmarks have published results for both models. Mistral Small 3 has 24 scored results on Noometry and Qwen3.8 27B has 28.