Model comparison
DeepSeek V4 Flash vs Ministral 8B
DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 28.2 on the Noometry Index. Ministral 8B costs 1.7× less per token, which makes it the better buy when DeepSeek V4 Flash's lead doesn't matter for your workload.
Last verified . 14 shared benchmarks.
DeepSeek
Mistral AISummary
- They share 14 benchmarks with published results for both. DeepSeek V4 Flash scores higher in 8 categories and Ministral 8B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where DeepSeek V4 Flash leads 55.4 to 12.6.
- The biggest single-benchmark swing is GPQA Diamond: 91% for DeepSeek V4 Flash and 27.1% for Ministral 8B.
- Ministral 8B is cheaper at $0.15 / $0.15 per million input/output tokens, against $0.15 / $0.60 for DeepSeek V4 Flash.
- DeepSeek V4 Flash accepts more context: 1M tokens versus 262K.
Side by side
| DeepSeek V4 Flash | Ministral 8B | |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 53.6 | 28.2 |
| Released | 2026-04-24 | 2024-10-01 |
| Weights | Open | Open |
| Context window | 1M | 262K |
| Max output | 393K | 262K |
| Input $ / M tokens | $0.15 | $0.15 |
| Output $ / M tokens | $0.60 | $0.15 |
| Results tracked | 41 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek V4 Flash leads
DeepSeek V4 Flash: 47.9 (#59), Ministral 8B: 35.0 (#230)
| Benchmark | DeepSeek V4 Flash | Ministral 8B |
|---|---|---|
| LMArena Coding | 1457 | 1202 |
| FrontierCode | 18.8% | — |
| LMArena WebDev | 1582 | — |
| SciCode | 49.9% | — |
| WeirdML | 63% | — |
| ALE-Bench | 1,306 | — |
Agentic & Tool Use Not comparable
DeepSeek V4 Flash: —, Ministral 8B: 16.4 (#148)
| Benchmark | DeepSeek V4 Flash | Ministral 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 11.1% |
Reasoning DeepSeek V4 Flash leads
DeepSeek V4 Flash: 53.7 (#30), Ministral 8B: 18.4 (#281)
| Benchmark | DeepSeek V4 Flash | Ministral 8B |
|---|---|---|
| LMArena Hard Prompts | 1444 | 1191 |
| DTBench | 90.9% | 45.7% |
| ARC-AGI-2 | 61.4% | — |
| SimpleBench | 61.1% | — |
| Kagi LLM Benchmark | 52.2% | — |
| NYT Connections (extended) | 89.6% | — |
| ARC-AGI-1 | 89% | — |
| CritPt | 16.6% | — |
| Chess Puzzles | 33% | — |
| Mystery Game Puzzles | 34% | — |
| LMCA | 41.7% | — |
| Epoch Capabilities Index | 154.49 | — |
Math DeepSeek V4 Flash leads
DeepSeek V4 Flash: 60.3 (#37), Ministral 8B: 25.7 (#267)
| Benchmark | DeepSeek V4 Flash | Ministral 8B |
|---|---|---|
| LMArena Math | 1427 | 1188 |
| FrontierMath (Tiers 1-3) | 57.5% | — |
| FrontierMath Tier 4 | 24.4% | — |
| MathArena Final-Answer Competitions | 76.5% | — |
| OTIS Mock AIME 2024-2025 | 94.4% | — |
| ProofBench | 56% | — |
| MATH Level 5 | — | 14.9% |
Knowledge DeepSeek V4 Flash leads
DeepSeek V4 Flash: 55.4 (#48), Ministral 8B: 12.6 (#297)
| Benchmark | DeepSeek V4 Flash | Ministral 8B |
|---|---|---|
| GPQA Diamond | 91% | 27.1% |
| LMArena Expert | 1441 | 1170 |
| SimpleQA Verified | 33.6% | — |
| Vectara Hallucination Rate | — | 7.4% |
Multilingual DeepSeek V4 Flash leads
DeepSeek V4 Flash: 53.0 (#72), Ministral 8B: 35.1 (#247)
| Benchmark | DeepSeek V4 Flash | Ministral 8B |
|---|---|---|
| LMArena Non-English | 1420 | 1165 |
| LMArena Chinese | 1468 | 1193 |
| LMArena Russian | 1428 | 1195 |
| LMArena French | 1439 | — |
| LMArena German | 1418 | — |
| LMArena Japanese | 1406 | — |
| LMArena Korean | 1384 | — |
| LMArena Spanish | 1436 | — |
Instruction Following DeepSeek V4 Flash leads
DeepSeek V4 Flash: 74.9 (#81), Ministral 8B: 60.5 (#250)
| Benchmark | DeepSeek V4 Flash | Ministral 8B |
|---|---|---|
| LMArena Instruction Following | 1421 | 1161 |
Long Context DeepSeek V4 Flash leads
DeepSeek V4 Flash: 43.8 (#85), Ministral 8B: 36.7 (#227)
| Benchmark | DeepSeek V4 Flash | Ministral 8B |
|---|---|---|
| LMArena Longer Query | 1434 | 1212 |
Writing & Preference DeepSeek V4 Flash leads
DeepSeek V4 Flash: 63.8 (#61), Ministral 8B: 39.6 (#246)
| Benchmark | DeepSeek V4 Flash | Ministral 8B |
|---|---|---|
| LMArena Text | 1432 | 1191 |
| LMArena Creative Writing | 1403 | 1175 |
| LMArena Multi-Turn | 1449 | 1166 |
| EQ-Bench Creative Writing | 1559 | — |
Frequently asked questions
Is DeepSeek V4 Flash better than Ministral 8B?
DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 28.2 on the Noometry Index. Ministral 8B costs 1.7× less per token, which makes it the better buy when DeepSeek V4 Flash's lead doesn't matter for your workload.
Which is cheaper, DeepSeek V4 Flash or Ministral 8B?
Ministral 8B is cheaper. It lists at $0.15 per million input tokens and $0.15 per million output tokens; DeepSeek V4 Flash lists at $0.15 and $0.60.
Is DeepSeek V4 Flash or Ministral 8B better for coding?
DeepSeek V4 Flash scores higher on coding benchmarks: 47.9 versus 35.0 in the Noometry coding category.
Which has the bigger context window?
DeepSeek V4 Flash does, with 1M tokens against 262K.
How many benchmarks do DeepSeek V4 Flash and Ministral 8B share?
14 benchmarks have published results for both models. DeepSeek V4 Flash has 41 scored results on Noometry and Ministral 8B has 17.