Model comparison
Codestral vs DeepSeek V4.1 Flash
DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 30.6 on the Noometry Index.
Last verified . 1 shared benchmarks.
Mistral AI
DeepSeekSummary
- They share 1 benchmark with published results for both. Codestral scores higher in 0 categories and DeepSeek V4.1 Flash in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4.1 Flash leads 50.2 to 19.8.
- DeepSeek V4.1 Flash is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.30 / $0.90 for Codestral.
- DeepSeek V4.1 Flash accepts more context: 1M tokens versus 256K.
- DeepSeek V4.1 Flash has downloadable open weights; the other is API-only.
Side by side
| Codestral | DeepSeek V4.1 Flash | |
|---|---|---|
| Provider | Mistral AI | DeepSeek |
| Noometry Index | 30.6 | 52.8 |
| Released | 2024-05-29 | 2026-09-09 |
| Weights | Proprietary | Open |
| Context window | 256K | 1M |
| Max output | 8K | 393K |
| Input $ / M tokens | $0.30 | $0.15 |
| Output $ / M tokens | $0.90 | $0.60 |
| Results tracked | 7 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek V4.1 Flash leads
Codestral: 27.3 (#321), DeepSeek V4.1 Flash: 52.9 (#32)
| Benchmark | Codestral | DeepSeek V4.1 Flash |
|---|---|---|
| ALE-Bench | 137.78 | 1,092 |
| Aider Polyglot | 11.1% | — |
| LMArena WebDev | — | 1619 |
| SciCode | — | 51.9% |
| BigCodeBench Instruct | 41.8% | — |
| LMArena Coding | — | 1506 |
| BigCodeBench Complete | 52.5% | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |
Agentic & Tool Use Not comparable
Codestral: —, DeepSeek V4.1 Flash: 31.2 (#69)
| Benchmark | Codestral | DeepSeek V4.1 Flash |
|---|---|---|
| APEX-Agents | — | 39.5% |
| GDP.pdf | — | 19.8% |
Reasoning DeepSeek V4.1 Flash leads
Codestral: 19.8 (#251), DeepSeek V4.1 Flash: 50.2 (#36)
| Benchmark | Codestral | DeepSeek V4.1 Flash |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| NYT Connections (extended) | — | 89.6% |
| CritPt | — | 14.3% |
| LMArena Hard Prompts | — | 1483 |
| Mystery Game Puzzles | — | 43% |
| DTBench | — | 89.9% |
| LMCA | — | 47% |
| Surface Evolver Bench | — | 46.3% |
| Epoch Capabilities Index | — | 154.9 |
Math Not comparable
Codestral: —, DeepSeek V4.1 Flash: 66.7 (#25)
| Benchmark | Codestral | DeepSeek V4.1 Flash |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 67.4% |
| FrontierMath Tier 4 | — | 26.8% |
| OTIS Mock AIME 2024-2025 | — | 98.3% |
| ProofBench | — | 54% |
| LMArena Math | — | 1477 |
Knowledge Not comparable
Codestral: —, DeepSeek V4.1 Flash: 57.9 (#38)
| Benchmark | Codestral | DeepSeek V4.1 Flash |
|---|---|---|
| GPQA Diamond | — | 89.8% |
| LMArena Expert | — | 1506 |
Multimodal Not comparable
Codestral: —, DeepSeek V4.1 Flash: 39.1 (#61)
| Benchmark | Codestral | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Vision | — | 1277 |
| Furniture Assembly | — | 34.2% |
Multilingual Not comparable
Codestral: —, DeepSeek V4.1 Flash: 55.0 (#35)
| Benchmark | Codestral | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Non-English | — | 1448 |
| LMArena Chinese | — | 1497 |
| LMArena French | — | 1452 |
| LMArena German | — | 1484 |
| LMArena Japanese | — | 1412 |
| LMArena Korean | — | 1452 |
| LMArena Russian | — | 1471 |
| LMArena Spanish | — | 1459 |
Instruction Following Not comparable
Codestral: —, DeepSeek V4.1 Flash: 77.3 (#26)
| Benchmark | Codestral | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Instruction Following | — | 1474 |
Long Context Not comparable
Codestral: —, DeepSeek V4.1 Flash: 45.2 (#47)
| Benchmark | Codestral | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Longer Query | — | 1475 |
Writing & Preference Not comparable
Codestral: —, DeepSeek V4.1 Flash: 65.4 (#48)
| Benchmark | Codestral | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Text | — | 1462 |
| LMArena Creative Writing | — | 1435 |
| EQ-Bench Creative Writing | — | 1540 |
| LMArena Multi-Turn | — | 1457 |
Frequently asked questions
Is Codestral better than DeepSeek V4.1 Flash?
DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 30.6 on the Noometry Index.
Which is cheaper, Codestral or DeepSeek V4.1 Flash?
DeepSeek V4.1 Flash is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Codestral lists at $0.30 and $0.90.
Is Codestral or DeepSeek V4.1 Flash better for coding?
DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.9 versus 27.3 in the Noometry coding category.
Which has the bigger context window?
DeepSeek V4.1 Flash does, with 1M tokens against 256K.
How many benchmarks do Codestral and DeepSeek V4.1 Flash share?
1 benchmark has published results for both models. Codestral has 7 scored results on Noometry and DeepSeek V4.1 Flash has 37.