Model comparison
DeepSeek V4.1 Flash vs Mistral Small
DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 33.4 on the Noometry Index.
Last verified . 25 shared benchmarks.
DeepSeek
Mistral AISummary
- They share 25 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 10 categories and Mistral Small in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek V4.1 Flash leads 66.7 to 16.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 98.3% for DeepSeek V4.1 Flash and 5.8% for Mistral Small.
- Both cost about the same: $0.15 input and $0.60 output per million tokens.
- DeepSeek V4.1 Flash accepts more context: 1M tokens versus 262K.
Side by side
| DeepSeek V4.1 Flash | Mistral Small | |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 52.8 | 33.4 |
| Released | 2026-09-09 | 2024-02-26 |
| Weights | Open | Open |
| Context window | 1M | 262K |
| Max output | 393K | 256K |
| Input $ / M tokens | $0.15 | $0.15 |
| Output $ / M tokens | $0.60 | $0.60 |
| Results tracked | 37 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 52.9 (#32), Mistral Small: 34.0 (#247)
| Benchmark | DeepSeek V4.1 Flash | Mistral Small |
|---|---|---|
| SciCode | 51.9% | 26.5% |
| LMArena Coding | 1506 | 1362 |
| ALE-Bench | 1,092 | 497.62 |
| LMArena WebDev | 1619 | — |
| BigCodeBench Instruct | — | 36.1% |
| LiveBench Coding | — | 36.2% |
| BigCodeBench Complete | — | 46.6% |
Agentic & Tool Use DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 31.2 (#69), Mistral Small: 28.1 (#93)
| Benchmark | DeepSeek V4.1 Flash | Mistral Small |
|---|---|---|
| APEX-Agents | 39.5% | — |
| Berkeley Function Calling Leaderboard | — | 37.1% |
| GDP.pdf | 19.8% | — |
Reasoning DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 50.2 (#36), Mistral Small: 19.8 (#250)
| Benchmark | DeepSeek V4.1 Flash | Mistral Small |
|---|---|---|
| CritPt | 14.3% | 0% |
| LMArena Hard Prompts | 1483 | 1335 |
| DTBench | 89.9% | 70.9% |
| LMCA | 47% | 20.6% |
| Kagi LLM Benchmark | — | 37.8% |
| NYT Connections (extended) | 89.6% | — |
| LiveBench Reasoning | — | 44.8% |
| Mystery Game Puzzles | 43% | — |
| LiveBench Data Analysis | — | 53.7% |
| Surface Evolver Bench | 46.3% | — |
| Epoch Capabilities Index | 154.9 | — |
| LiveBench | — | 44% |
Math DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 66.7 (#25), Mistral Small: 16.4 (#293)
| Benchmark | DeepSeek V4.1 Flash | Mistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 98.3% | 5.8% |
| LMArena Math | 1477 | 1341 |
| FrontierMath (Tiers 1-3) | 67.4% | — |
| FrontierMath Tier 4 | 26.8% | — |
| ProofBench | 54% | — |
| LiveBench Math | — | 39.9% |
| MATH Level 5 | — | 46.8% |
Knowledge DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 57.9 (#38), Mistral Small: 31.0 (#222)
| Benchmark | DeepSeek V4.1 Flash | Mistral Small |
|---|---|---|
| GPQA Diamond | 89.8% | 47.5% |
| LMArena Expert | 1506 | 1291 |
| Vectara Hallucination Rate | — | 5.1% |
| MMLU | — | 68.7% |
Multimodal DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 39.1 (#61), Mistral Small: 33.5 (#96)
| Benchmark | DeepSeek V4.1 Flash | Mistral Small |
|---|---|---|
| LMArena Vision | 1277 | 1142 |
| Furniture Assembly | 34.2% | — |
Multilingual DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 55.0 (#35), Mistral Small: 45.5 (#169)
| Benchmark | DeepSeek V4.1 Flash | Mistral Small |
|---|---|---|
| LMArena Non-English | 1448 | 1315 |
| LMArena Chinese | 1497 | 1340 |
| LMArena French | 1452 | 1337 |
| LMArena German | 1484 | 1340 |
| LMArena Japanese | 1412 | 1275 |
| LMArena Korean | 1452 | 1259 |
| LMArena Russian | 1471 | 1324 |
| LMArena Spanish | 1459 | 1346 |
Instruction Following DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 77.3 (#26), Mistral Small: 66.4 (#209)
| Benchmark | DeepSeek V4.1 Flash | Mistral Small |
|---|---|---|
| LMArena Instruction Following | 1474 | 1310 |
| LiveBench Instruction Following | — | 63.7% |
Long Context DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 45.2 (#47), Mistral Small: 40.4 (#156)
| Benchmark | DeepSeek V4.1 Flash | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1475 | 1327 |
Writing & Preference DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 65.4 (#48), Mistral Small: 52.5 (#171)
| Benchmark | DeepSeek V4.1 Flash | Mistral Small |
|---|---|---|
| LMArena Text | 1462 | 1338 |
| LMArena Creative Writing | 1435 | 1305 |
| LMArena Multi-Turn | 1457 | 1344 |
| EQ-Bench Creative Writing | 1540 | — |
| LiveBench Language | — | 30.5% |
Frequently asked questions
Is DeepSeek V4.1 Flash better than Mistral Small?
DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 33.4 on the Noometry Index.
Which is cheaper, DeepSeek V4.1 Flash or Mistral Small?
Mistral Small is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; DeepSeek V4.1 Flash lists at $0.15 and $0.60.
Is DeepSeek V4.1 Flash or Mistral Small better for coding?
DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.9 versus 34.0 in the Noometry coding category.
Which has the bigger context window?
DeepSeek V4.1 Flash does, with 1M tokens against 262K.
How many benchmarks do DeepSeek V4.1 Flash and Mistral Small share?
25 benchmarks have published results for both models. DeepSeek V4.1 Flash has 37 scored results on Noometry and Mistral Small has 39.