Model comparison
DeepSeek V4 Pro vs Mistral Nemo
DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 26.4 on the Noometry Index. Mistral Nemo costs 6.6× less per token, which makes it the better buy when DeepSeek V4 Pro's lead doesn't matter for your workload.
Last verified . 4 shared benchmarks.
DeepSeek
Mistral AISummary
- They share 4 benchmarks with published results for both. DeepSeek V4 Pro scores higher in 5 categories and Mistral Nemo in 0 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where DeepSeek V4 Pro leads 59.5 to 12.3.
- The biggest single-benchmark swing is GPQA Diamond: 91.7% for DeepSeek V4 Pro and 29.9% for Mistral Nemo.
- Mistral Nemo is cheaper at $0.15 / $0.15 per million input/output tokens, against $0.66 / $1.98 for DeepSeek V4 Pro.
- DeepSeek V4 Pro accepts more context: 1M tokens versus 128K.
Side by side
| DeepSeek V4 Pro | Mistral Nemo | |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 54.3 | 26.4 |
| Released | 2026-04-24 | 2024-07-01 |
| Weights | Open | Open |
| Context window | 1M | 128K |
| Max output | 393K | 128K |
| Input $ / M tokens | $0.66 | $0.15 |
| Output $ / M tokens | $1.98 | $0.15 |
| Results tracked | 48 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
DeepSeek V4 Pro: 52.4 (#34), Mistral Nemo: —
| Benchmark | DeepSeek V4 Pro | Mistral Nemo |
|---|---|---|
| SWE-bench Verified | 77.6% | — |
| FrontierCode | 28.6% | — |
| LMArena WebDev | 1582 | — |
| SciCode | 51% | — |
| WeirdML | 66.2% | — |
| LMArena Coding | 1470 | — |
| ALE-Bench | 1,403 | — |
Agentic & Tool Use DeepSeek V4 Pro leads
DeepSeek V4 Pro: 32.8 (#58), Mistral Nemo: 23.5 (#125)
| Benchmark | DeepSeek V4 Pro | Mistral Nemo |
|---|---|---|
| APEX-Agents | 47.3% | — |
| Berkeley Function Calling Leaderboard | — | 27.6% |
| BALROG | — | 17.6% |
| Vending-Bench 2 | 3,285 | — |
Reasoning DeepSeek V4 Pro leads
DeepSeek V4 Pro: 56.5 (#24), Mistral Nemo: 20.7 (#232)
| Benchmark | DeepSeek V4 Pro | Mistral Nemo |
|---|---|---|
| DTBench | 93.9% | 48.6% |
| Epoch Capabilities Index | 155.31 | 118.68 |
| ARC-AGI-2 | 61.3% | — |
| Kagi LLM Benchmark | 53.5% | — |
| NYT Connections (extended) | 91.3% | — |
| ARC-AGI-1 | 90.5% | — |
| CritPt | 18% | — |
| Chess Puzzles | 47% | — |
| LMArena Hard Prompts | 1461 | — |
| Mystery Game Puzzles | 43% | — |
| LMCA | 45.5% | — |
| Surface Evolver Bench | 40% | — |
| ForecastBench | 56.1 | — |
| PIQA | — | 83.5% |
Math DeepSeek V4 Pro leads
DeepSeek V4 Pro: 64.8 (#30), Mistral Nemo: 25.5 (#268)
| Benchmark | DeepSeek V4 Pro | Mistral Nemo |
|---|---|---|
| FrontierMath (Tiers 1-3) | 64.6% | — |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 76.6% | — |
| OTIS Mock AIME 2024-2025 | 98.6% | — |
| ProofBench | 50% | — |
| LMArena Math | 1455 | — |
| MATH Level 5 | — | 10.8% |
| GSM8K | — | 84.2% |
Knowledge DeepSeek V4 Pro leads
DeepSeek V4 Pro: 59.5 (#31), Mistral Nemo: 12.3 (#298)
| Benchmark | DeepSeek V4 Pro | Mistral Nemo |
|---|---|---|
| GPQA Diamond | 91.7% | 29.9% |
| SimpleQA Verified | 52.9% | — |
| Vectara Hallucination Rate | 8.6% | — |
| LMArena Expert | 1464 | — |
| BoolQ | — | 82.5% |
Multilingual Not comparable
DeepSeek V4 Pro: 54.4 (#45), Mistral Nemo: —
| Benchmark | DeepSeek V4 Pro | Mistral Nemo |
|---|---|---|
| LMArena Non-English | 1439 | — |
| LMArena Chinese | 1486 | — |
| LMArena French | 1472 | — |
| LMArena German | 1458 | — |
| LMArena Japanese | 1445 | — |
| LMArena Korean | 1447 | — |
| LMArena Russian | 1453 | — |
| LMArena Spanish | 1458 | — |
Instruction Following Not comparable
DeepSeek V4 Pro: 76.1 (#47), Mistral Nemo: —
| Benchmark | DeepSeek V4 Pro | Mistral Nemo |
|---|---|---|
| LMArena Instruction Following | 1448 | — |
Long Context Not comparable
DeepSeek V4 Pro: 45.0 (#51), Mistral Nemo: —
| Benchmark | DeepSeek V4 Pro | Mistral Nemo |
|---|---|---|
| CL-bench Life | 13.5% | — |
| LMArena Longer Query | 1458 | — |
Writing & Preference DeepSeek V4 Pro leads
DeepSeek V4 Pro: 65.5 (#46), Mistral Nemo: 28.5 (#296)
| Benchmark | DeepSeek V4 Pro | Mistral Nemo |
|---|---|---|
| EQ-Bench Creative Writing | 1553 | 881 |
| LMArena Text | 1451 | — |
| LMArena Creative Writing | 1446 | — |
| EQ-Bench 4 | 1166 | — |
| LMArena Multi-Turn | 1467 | — |
Frequently asked questions
Is DeepSeek V4 Pro better than Mistral Nemo?
DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 26.4 on the Noometry Index. Mistral Nemo costs 6.6× less per token, which makes it the better buy when DeepSeek V4 Pro's lead doesn't matter for your workload.
Which is cheaper, DeepSeek V4 Pro or Mistral Nemo?
Mistral Nemo is cheaper. It lists at $0.15 per million input tokens and $0.15 per million output tokens; DeepSeek V4 Pro lists at $0.66 and $1.98.
Which has the bigger context window?
DeepSeek V4 Pro does, with 1M tokens against 128K.
How many benchmarks do DeepSeek V4 Pro and Mistral Nemo share?
4 benchmarks have published results for both models. DeepSeek V4 Pro has 48 scored results on Noometry and Mistral Nemo has 10.