Model comparison
DeepSeek-V3.2-Exp vs Mixtral 8x22B
DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.9 to 26.7 on the Noometry Index.
Last verified . 21 shared benchmarks.
DeepSeek
Mistral AISummary
- They share 21 benchmarks with published results for both. DeepSeek-V3.2-Exp scores higher in 9 categories and Mixtral 8x22B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where DeepSeek-V3.2-Exp leads 51.6 to 15.1.
- The biggest single-benchmark swing is GPQA Diamond: 83.4% for DeepSeek-V3.2-Exp and 34.1% for Mixtral 8x22B.
- DeepSeek-V3.2-Exp is cheaper at $0.26 / $0.38 per million input/output tokens, against $2 / $6 for Mixtral 8x22B.
- DeepSeek-V3.2-Exp accepts more context: 164K tokens versus 64K.
Side by side
| DeepSeek-V3.2-Exp | Mixtral 8x22B | |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 44.9 | 26.7 |
| Released | 2025-09-29 | 2024-04-17 |
| Weights | Open | Open |
| Context window | 164K | 64K |
| Max output | 66K | 64K |
| Input $ / M tokens | $0.26 | $2 |
| Output $ / M tokens | $0.38 | $6 |
| Results tracked | 48 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 46.4 (#61), Mixtral 8x22B: 23.8 (#324)
| Benchmark | DeepSeek-V3.2-Exp | Mixtral 8x22B |
|---|---|---|
| WeirdML | 39.5% | 3.2% |
| LMArena Coding | 1454 | 1166 |
| SWE-bench Verified (bash only) | 70% | — |
| Aider Polyglot | 74.2% | — |
| LMArena WebDev | 1362 | — |
| SWE-bench Multilingual | 59% | — |
| SciCode | 38.9% | — |
| BigCodeBench Instruct | — | 40.6% |
| BigCodeBench Complete | — | 50.2% |
| HumanEval+ | — | 72% |
| MBPP+ | — | 64.3% |
Agentic & Tool Use DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 37.9 (#31), Mixtral 8x22B: 22.8 (#119)
| Benchmark | DeepSeek-V3.2-Exp | Mixtral 8x22B |
|---|---|---|
| Terminal-Bench | 39.6% | — |
| Berkeley Function Calling Leaderboard | 56.7% | — |
| TheAgentCompany | 42.9% | — |
| Cybench | — | 7.5% |
| Vending-Bench 2 | 1,034 | — |
Reasoning DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 22.0 (#185), Mixtral 8x22B: 19.1 (#246)
| Benchmark | DeepSeek-V3.2-Exp | Mixtral 8x22B |
|---|---|---|
| LMArena Hard Prompts | 1433 | 1150 |
| DTBench | 87.7% | 55.1% |
| Epoch Capabilities Index | 146.28 | 122 |
| ARC-AGI-2 | 4% | — |
| Kagi LLM Benchmark | 52.2% | — |
| NYT Connections (extended) | 36.7% | — |
| ARC-AGI-1 | 57% | — |
| CritPt | 2.9% | — |
| Chess Puzzles | 14% | — |
| Thematic Generalization | 65% | — |
| LMCA | 29.1% | — |
| ForecastBench | — | 56.3 |
Math DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 40.8 (#75), Mixtral 8x22B: 21.2 (#271)
| Benchmark | DeepSeek-V3.2-Exp | Mixtral 8x22B |
|---|---|---|
| LMArena Math | 1435 | 1184 |
| MathArena Final-Answer Competitions | 57.7% | — |
| OTIS Mock AIME 2024-2025 | 87.8% | — |
| ProofBench | 8% | — |
| Omni-MATH | — | 16.3% |
| MATH Level 5 | — | 24.2% |
| FrontierMath (Feb 2025 set) | 22.1% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 51.6 (#61), Mixtral 8x22B: 15.1 (#288)
| Benchmark | DeepSeek-V3.2-Exp | Mixtral 8x22B |
|---|---|---|
| GPQA Diamond | 83.4% | 34.1% |
| LMArena Expert | 1436 | 1113 |
| MMLU-Pro | — | 46% |
| Vectara Hallucination Rate | 5.3% | — |
| GPQA (HELM) | — | 33.4% |
| MMLU | — | 77.8% |
Multilingual DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 52.4 (#85), Mixtral 8x22B: 32.9 (#250)
| Benchmark | DeepSeek-V3.2-Exp | Mixtral 8x22B |
|---|---|---|
| LMArena Non-English | 1409 | 1128 |
| LMArena Chinese | 1461 | 1116 |
| LMArena French | 1435 | 1165 |
| LMArena German | 1440 | 1141 |
| LMArena Japanese | 1377 | 1037 |
| LMArena Korean | 1372 | 1056 |
| LMArena Russian | 1423 | 1158 |
| LMArena Spanish | 1441 | 1150 |
Instruction Following DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 74.7 (#89), Mixtral 8x22B: 57.9 (#261)
| Benchmark | DeepSeek-V3.2-Exp | Mixtral 8x22B |
|---|---|---|
| LMArena Instruction Following | 1413 | 1147 |
| IFEval | — | 72.4% |
Long Context DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 47.6 (#15), Mixtral 8x22B: 34.6 (#242)
| Benchmark | DeepSeek-V3.2-Exp | Mixtral 8x22B |
|---|---|---|
| LMArena Longer Query | 1428 | 1144 |
| Fiction.LiveBench | 83.3% | — |
| CL-bench | 13.2% | — |
| CL-bench Life | 9.5% | — |
Writing & Preference DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 62.5 (#73), Mixtral 8x22B: 37.1 (#257)
| Benchmark | DeepSeek-V3.2-Exp | Mixtral 8x22B |
|---|---|---|
| LMArena Text | 1425 | 1162 |
| LMArena Creative Writing | 1403 | 1141 |
| LMArena Multi-Turn | 1427 | 1130 |
| EQ-Bench Creative Writing | 1515 | — |
| WildBench | — | 71.1% |
Frequently asked questions
Is DeepSeek-V3.2-Exp better than Mixtral 8x22B?
DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.9 to 26.7 on the Noometry Index.
Which is cheaper, DeepSeek-V3.2-Exp or Mixtral 8x22B?
DeepSeek-V3.2-Exp is cheaper. It lists at $0.26 per million input tokens and $0.38 per million output tokens; Mixtral 8x22B lists at $2 and $6.
Is DeepSeek-V3.2-Exp or Mixtral 8x22B better for coding?
DeepSeek-V3.2-Exp scores higher on coding benchmarks: 46.4 versus 23.8 in the Noometry coding category.
Which has the bigger context window?
DeepSeek-V3.2-Exp does, with 164K tokens against 64K.
How many benchmarks do DeepSeek-V3.2-Exp and Mixtral 8x22B share?
21 benchmarks have published results for both models. DeepSeek-V3.2-Exp has 48 scored results on Noometry and Mixtral 8x22B has 34.