Model comparison
DeepSeek V4 Pro vs WizardLM-2 8x22B
DeepSeek V4 Pro has enough public results to be ranked (#31); WizardLM-2 8x22B does not yet, so treat this comparison as directional.
Last verified . 1 shared benchmarks.
DeepSeek
MicrosoftSummary
- They share 1 benchmark with published results for both. DeepSeek V4 Pro scores higher in 2 categories and WizardLM-2 8x22B in 0 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where DeepSeek V4 Pro leads 59.5 to 23.3.
- The biggest single-benchmark swing is GPQA Diamond: 91.7% for DeepSeek V4 Pro and 43.4% for WizardLM-2 8x22B.
- WizardLM-2 8x22B is cheaper at $0.62 / $0.62 per million input/output tokens, against $0.66 / $1.98 for DeepSeek V4 Pro.
- DeepSeek V4 Pro accepts more context: 1M tokens versus 66K.
Side by side
| DeepSeek V4 Pro | WizardLM-2 8x22B | |
|---|---|---|
| Provider | DeepSeek | Microsoft |
| Noometry Index | 54.3 | 31.4 |
| Released | 2026-04-24 | 2024-04-15 |
| Weights | Open | Open |
| Context window | 1M | 66K |
| Max output | 393K | 8K |
| Input $ / M tokens | $0.66 | $0.62 |
| Output $ / M tokens | $1.98 | $0.62 |
| Results tracked | 48 | 2 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
DeepSeek V4 Pro: 52.4 (#34), WizardLM-2 8x22B: —
| Benchmark | DeepSeek V4 Pro | WizardLM-2 8x22B |
|---|---|---|
| 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 Not comparable
DeepSeek V4 Pro: 32.8 (#58), WizardLM-2 8x22B: —
| Benchmark | DeepSeek V4 Pro | WizardLM-2 8x22B |
|---|---|---|
| APEX-Agents | 47.3% | — |
| Vending-Bench 2 | 3,285 | — |
Reasoning Not comparable
DeepSeek V4 Pro: 56.5 (#24), WizardLM-2 8x22B: —
| Benchmark | DeepSeek V4 Pro | WizardLM-2 8x22B |
|---|---|---|
| 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% | — |
| DTBench | 93.9% | — |
| LMCA | 45.5% | — |
| Surface Evolver Bench | 40% | — |
| Epoch Capabilities Index | 155.31 | — |
| ForecastBench | 56.1 | — |
Math DeepSeek V4 Pro leads
DeepSeek V4 Pro: 64.8 (#30), WizardLM-2 8x22B: 28.9
| Benchmark | DeepSeek V4 Pro | WizardLM-2 8x22B |
|---|---|---|
| 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 | — | 25.7% |
Knowledge DeepSeek V4 Pro leads
DeepSeek V4 Pro: 59.5 (#31), WizardLM-2 8x22B: 23.3
| Benchmark | DeepSeek V4 Pro | WizardLM-2 8x22B |
|---|---|---|
| GPQA Diamond | 91.7% | 43.4% |
| SimpleQA Verified | 52.9% | — |
| Vectara Hallucination Rate | 8.6% | — |
| LMArena Expert | 1464 | — |
Multilingual Not comparable
DeepSeek V4 Pro: 54.4 (#45), WizardLM-2 8x22B: —
| Benchmark | DeepSeek V4 Pro | WizardLM-2 8x22B |
|---|---|---|
| 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), WizardLM-2 8x22B: —
| Benchmark | DeepSeek V4 Pro | WizardLM-2 8x22B |
|---|---|---|
| LMArena Instruction Following | 1448 | — |
Long Context Not comparable
DeepSeek V4 Pro: 45.0 (#51), WizardLM-2 8x22B: —
| Benchmark | DeepSeek V4 Pro | WizardLM-2 8x22B |
|---|---|---|
| CL-bench Life | 13.5% | — |
| LMArena Longer Query | 1458 | — |
Writing & Preference Not comparable
DeepSeek V4 Pro: 65.5 (#46), WizardLM-2 8x22B: —
| Benchmark | DeepSeek V4 Pro | WizardLM-2 8x22B |
|---|---|---|
| LMArena Text | 1451 | — |
| LMArena Creative Writing | 1446 | — |
| EQ-Bench Creative Writing | 1553 | — |
| EQ-Bench 4 | 1166 | — |
| LMArena Multi-Turn | 1467 | — |
Frequently asked questions
Is DeepSeek V4 Pro better than WizardLM-2 8x22B?
DeepSeek V4 Pro has enough public results to be ranked (#31); WizardLM-2 8x22B does not yet, so treat this comparison as directional.
Which is cheaper, DeepSeek V4 Pro or WizardLM-2 8x22B?
WizardLM-2 8x22B is cheaper. It lists at $0.62 per million input tokens and $0.62 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 66K.
How many benchmarks do DeepSeek V4 Pro and WizardLM-2 8x22B share?
1 benchmark has published results for both models. DeepSeek V4 Pro has 48 scored results on Noometry and WizardLM-2 8x22B has 2.