Model comparison
DeepSeek-R1 vs Mixtral 8x7B
DeepSeek-R1 is the stronger model overall, scoring 42.3 to 27.1 on the Noometry Index.
Last verified . 26 shared benchmarks.
DeepSeek
Mistral AISummary
- They share 26 benchmarks with published results for both. DeepSeek-R1 scores higher in 8 categories and Mixtral 8x7B in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where DeepSeek-R1 leads 44.5 to 11.0.
- The biggest single-benchmark swing is MATH Level 5: 96.6% for DeepSeek-R1 and 10% for Mixtral 8x7B.
- Mixtral 8x7B is cheaper at $0.70 / $0.70 per million input/output tokens, against $0.50 / $2.15 for DeepSeek-R1.
- DeepSeek-R1 accepts more context: 164K tokens versus 32K.
- Mixtral 8x7B has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-R1 | Mixtral 8x7B | |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 42.3 | 27.1 |
| Released | 2025-01-20 | 2023-12-11 |
| Weights | Proprietary | Open |
| Context window | 164K | 32K |
| Max output | 64K | 32K |
| Input $ / M tokens | $0.50 | $0.70 |
| Output $ / M tokens | $2.15 | $0.70 |
| Results tracked | 52 | 38 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-R1 leads
DeepSeek-R1: 46.3 (#68), Mixtral 8x7B: 32.8 (#269)
| Benchmark | DeepSeek-R1 | Mixtral 8x7B |
|---|---|---|
| LMArena Coding | 1427 | 1126 |
| Aider Polyglot | 71.4% | — |
| SciCode | 35.7% | — |
| WeirdML | 41.6% | — |
| LiveBench Coding | 66.7% | — |
| ALE-Bench | 804.12 | — |
| AlgoTune | 1.7 | — |
| HumanEval+ | — | 39.6% |
| MBPP+ | — | 49.7% |
Agentic & Tool Use Not comparable
DeepSeek-R1: 30.7 (#75), Mixtral 8x7B: —
| Benchmark | DeepSeek-R1 | Mixtral 8x7B |
|---|---|---|
| DeepResearch Bench | 35.1% | — |
| BALROG | 34.9% | — |
| METR Time Horizons | 53.8% | — |
Reasoning Too close to call
DeepSeek-R1: 18.6 (#278), Mixtral 8x7B: 18.2 (#285)
| Benchmark | DeepSeek-R1 | Mixtral 8x7B |
|---|---|---|
| LMArena Hard Prompts | 1416 | 1115 |
| Epoch Capabilities Index | 141.29 | 118.47 |
| ForecastBench | 60 | 56.3 |
| ARC-AGI-2 | 1.3% | — |
| SimpleBench | 40.8% | — |
| Kagi LLM Benchmark | 69.4% | — |
| ARC-AGI-1 | 21.2% | — |
| CritPt | 1.1% | — |
| LiveBench Reasoning | 83.2% | — |
| DTBench | — | 49.6% |
| LiveBench Data Analysis | 69.8% | — |
| Adversarial NLI | — | 55.2% |
| HellaSwag | — | 86.7% |
| LiveBench | 71.6% | — |
| PIQA | — | 83.6% |
| WinoGrande | — | 77.2% |
Math DeepSeek-R1 leads
DeepSeek-R1: 43.8 (#79), Mixtral 8x7B: 18.8 (#289)
| Benchmark | DeepSeek-R1 | Mixtral 8x7B |
|---|---|---|
| Omni-MATH | 42.4% | 10.5% |
| LMArena Math | 1400 | 1147 |
| MATH Level 5 | 96.6% | 10% |
| OTIS Mock AIME 2024-2025 | 66.4% | — |
| LiveBench Math | 80.7% | — |
| GSM8K | — | 74.4% |
Knowledge DeepSeek-R1 leads
DeepSeek-R1: 44.5 (#87), Mixtral 8x7B: 11.0 (#301)
| Benchmark | DeepSeek-R1 | Mixtral 8x7B |
|---|---|---|
| GPQA Diamond | 76.3% | 30.6% |
| MMLU-Pro | 79.3% | 33.5% |
| GPQA (HELM) | 66.6% | 29.6% |
| LMArena Expert | 1394 | 1088 |
| Confabulations | 12.7% | — |
| Vectara Hallucination Rate | 11.3% | — |
| ARC (AI2) Challenge | — | 87.3% |
| MMLU | — | 70.6% |
| OpenBookQA | — | 85.8% |
| TriviaQA | — | 82.2% |
Multilingual DeepSeek-R1 leads
DeepSeek-R1: 52.4 (#85), Mixtral 8x7B: 29.6 (#266)
| Benchmark | DeepSeek-R1 | Mixtral 8x7B |
|---|---|---|
| LMArena Non-English | 1412 | 1077 |
| LMArena Chinese | 1442 | 1055 |
| LMArena French | 1417 | 1166 |
| LMArena German | 1404 | 1114 |
| LMArena Japanese | 1391 | 931 |
| LMArena Korean | 1360 | 968 |
| LMArena Russian | 1423 | 1090 |
| LMArena Spanish | 1411 | 1111 |
Instruction Following DeepSeek-R1 leads
DeepSeek-R1: 72.0 (#143), Mixtral 8x7B: 51.0 (#297)
| Benchmark | DeepSeek-R1 | Mixtral 8x7B |
|---|---|---|
| IFEval | 78.4% | 57.5% |
| LMArena Instruction Following | 1382 | 1109 |
| LiveBench Instruction Following | 80.5% | — |
Long Context DeepSeek-R1 leads
DeepSeek-R1: 45.4 (#36), Mixtral 8x7B: 33.4 (#260)
| Benchmark | DeepSeek-R1 | Mixtral 8x7B |
|---|---|---|
| LMArena Longer Query | 1391 | 1103 |
| Fiction.LiveBench | 75% | — |
Writing & Preference DeepSeek-R1 leads
DeepSeek-R1: 61.4 (#88), Mixtral 8x7B: 34.2 (#270)
| Benchmark | DeepSeek-R1 | Mixtral 8x7B |
|---|---|---|
| LMArena Text | 1428 | 1132 |
| LMArena Creative Writing | 1405 | 1109 |
| WildBench | 82.8% | 67.3% |
| LMArena Multi-Turn | 1405 | 1115 |
| Short-Story Creative Writing | 83% | — |
| EQ-Bench Creative Writing | 1500 | — |
| LiveBench Language | 48.5% | — |
Frequently asked questions
Is DeepSeek-R1 better than Mixtral 8x7B?
DeepSeek-R1 is the stronger model overall, scoring 42.3 to 27.1 on the Noometry Index.
Which is cheaper, DeepSeek-R1 or Mixtral 8x7B?
Mixtral 8x7B is cheaper. It lists at $0.70 per million input tokens and $0.70 per million output tokens; DeepSeek-R1 lists at $0.50 and $2.15.
Is DeepSeek-R1 or Mixtral 8x7B better for coding?
DeepSeek-R1 scores higher on coding benchmarks: 46.3 versus 32.8 in the Noometry coding category.
Which has the bigger context window?
DeepSeek-R1 does, with 164K tokens against 32K.
How many benchmarks do DeepSeek-R1 and Mixtral 8x7B share?
26 benchmarks have published results for both models. DeepSeek-R1 has 52 scored results on Noometry and Mixtral 8x7B has 38.