Model comparison
DeepSeek V4.1 Flash vs Mistral Large
DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 31.9 on the Noometry Index.
Last verified . 26 shared benchmarks.
DeepSeek
Mistral AISummary
- They share 26 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 9 categories and Mistral Large in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek V4.1 Flash leads 66.7 to 18.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 98.3% for DeepSeek V4.1 Flash and 8.5% for Mistral Large.
- DeepSeek V4.1 Flash is cheaper at $0.15 / $0.60 per million input/output tokens, against $2 / $6 for Mistral Large.
- DeepSeek V4.1 Flash accepts more context: 1M tokens versus 131K.
Side by side
| DeepSeek V4.1 Flash | Mistral Large | |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 52.8 | 31.9 |
| Released | 2026-09-09 | 2024-02-26 |
| Weights | Open | Open |
| Context window | 1M | 131K |
| Max output | 393K | 16K |
| Input $ / M tokens | $0.15 | $2 |
| Output $ / M tokens | $0.60 | $6 |
| Results tracked | 37 | 51 |
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 Large: 34.3 (#240)
| Benchmark | DeepSeek V4.1 Flash | Mistral Large |
|---|---|---|
| SciCode | 51.9% | 36.2% |
| LMArena Coding | 1506 | 1277 |
| ALE-Bench | 1,092 | 264.7 |
| LMArena WebDev | 1619 | — |
| BigCodeBench Instruct | — | 30% |
| LiveBench Coding | — | 47.1% |
| BigCodeBench Complete | — | 38.3% |
| HumanEval+ | — | 62.2% |
| MBPP+ | — | 59.5% |
Agentic & Tool Use DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 31.2 (#69), Mistral Large: 28.6 (#89)
| Benchmark | DeepSeek V4.1 Flash | Mistral Large |
|---|---|---|
| APEX-Agents | 39.5% | — |
| Berkeley Function Calling Leaderboard | — | 38.4% |
| GDP.pdf | 19.8% | — |
Reasoning DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 50.2 (#36), Mistral Large: 15.8 (#310)
| Benchmark | DeepSeek V4.1 Flash | Mistral Large |
|---|---|---|
| CritPt | 14.3% | 0% |
| LMArena Hard Prompts | 1483 | 1257 |
| DTBench | 89.9% | 65.1% |
| LMCA | 47% | 16.7% |
| Epoch Capabilities Index | 154.9 | 128.52 |
| SimpleBench | — | 22.5% |
| NYT Connections (extended) | 89.6% | — |
| LiveBench Reasoning | — | 43.5% |
| Mystery Game Puzzles | 43% | — |
| LiveBench Data Analysis | — | 50.1% |
| Surface Evolver Bench | 46.3% | — |
| ForecastBench | — | 57.1 |
| LiveBench | — | 48.4% |
Math DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 66.7 (#25), Mistral Large: 18.2 (#291)
| Benchmark | DeepSeek V4.1 Flash | Mistral Large |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 98.3% | 8.5% |
| LMArena Math | 1477 | 1262 |
| FrontierMath (Tiers 1-3) | 67.4% | — |
| FrontierMath Tier 4 | 26.8% | — |
| ProofBench | 54% | — |
| Omni-MATH | — | 28.1% |
| LiveBench Math | — | 42.5% |
| MATH Level 5 | — | 50.3% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 57.9 (#38), Mistral Large: 30.1 (#230)
| Benchmark | DeepSeek V4.1 Flash | Mistral Large |
|---|---|---|
| GPQA Diamond | 89.8% | 51.3% |
| LMArena Expert | 1506 | 1232 |
| MMLU-Pro | — | 59.9% |
| Confabulations | — | 21.4% |
| Vectara Hallucination Rate | — | 4.5% |
| GPQA (HELM) | — | 43.5% |
| MMLU | — | 80% |
Multimodal Not comparable
DeepSeek V4.1 Flash: 39.1 (#61), Mistral Large: —
| Benchmark | DeepSeek V4.1 Flash | Mistral Large |
|---|---|---|
| LMArena Vision | 1277 | — |
| Furniture Assembly | 34.2% | — |
Multilingual DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 55.0 (#35), Mistral Large: 40.0 (#219)
| Benchmark | DeepSeek V4.1 Flash | Mistral Large |
|---|---|---|
| LMArena Non-English | 1448 | 1237 |
| LMArena Chinese | 1497 | 1240 |
| LMArena French | 1452 | 1325 |
| LMArena German | 1484 | 1254 |
| LMArena Japanese | 1412 | 1188 |
| LMArena Korean | 1452 | 1202 |
| LMArena Russian | 1471 | 1257 |
| LMArena Spanish | 1459 | 1268 |
Instruction Following DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 77.3 (#26), Mistral Large: 67.9 (#191)
| Benchmark | DeepSeek V4.1 Flash | Mistral Large |
|---|---|---|
| LMArena Instruction Following | 1474 | 1249 |
| LiveBench Instruction Following | — | 67.9% |
| IFEval | — | 87.7% |
Long Context DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 45.2 (#47), Mistral Large: 38.3 (#199)
| Benchmark | DeepSeek V4.1 Flash | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1475 | 1261 |
Writing & Preference DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 65.4 (#48), Mistral Large: 40.7 (#242)
| Benchmark | DeepSeek V4.1 Flash | Mistral Large |
|---|---|---|
| LMArena Text | 1462 | 1266 |
| LMArena Creative Writing | 1435 | 1243 |
| EQ-Bench Creative Writing | 1540 | 985 |
| LMArena Multi-Turn | 1457 | 1260 |
| Short-Story Creative Writing | — | 69% |
| WildBench | — | 80.1% |
| LiveBench Language | — | 39.4% |
Frequently asked questions
Is DeepSeek V4.1 Flash better than Mistral Large?
DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 31.9 on the Noometry Index.
Which is cheaper, DeepSeek V4.1 Flash or Mistral Large?
DeepSeek V4.1 Flash is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Mistral Large lists at $2 and $6.
Is DeepSeek V4.1 Flash or Mistral Large better for coding?
DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.9 versus 34.3 in the Noometry coding category.
Which has the bigger context window?
DeepSeek V4.1 Flash does, with 1M tokens against 131K.
How many benchmarks do DeepSeek V4.1 Flash and Mistral Large share?
26 benchmarks have published results for both models. DeepSeek V4.1 Flash has 37 scored results on Noometry and Mistral Large has 51.