Model comparison
DeepSeek V4 Pro vs Wizardlm 70b
DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 33.0 on the Noometry Index.
Last verified . 12 shared benchmarks.
DeepSeek
MicrosoftSummary
- They share 12 benchmarks with published results for both. DeepSeek V4 Pro scores higher in 7 categories and Wizardlm 70b in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4 Pro leads 56.5 to 20.7.
Side by side
| DeepSeek V4 Pro | Wizardlm 70b | |
|---|---|---|
| Provider | DeepSeek | Microsoft |
| Noometry Index | 54.3 | 33.0 |
| Released | 2026-04-24 | — |
| Weights | Open | Open |
| Context window | 1M | — |
| Max output | 393K | — |
| Input $ / M tokens | $0.66 | — |
| Output $ / M tokens | $1.98 | — |
| Results tracked | 48 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek V4 Pro leads
DeepSeek V4 Pro: 52.4 (#34), Wizardlm 70b: 31.4 (#285)
| Benchmark | DeepSeek V4 Pro | Wizardlm 70b |
|---|---|---|
| LMArena Coding | 1470 | 1081 |
| SWE-bench Verified | 77.6% | — |
| FrontierCode | 28.6% | — |
| LMArena WebDev | 1582 | — |
| SciCode | 51% | — |
| WeirdML | 66.2% | — |
| ALE-Bench | 1,403 | — |
Agentic & Tool Use Not comparable
DeepSeek V4 Pro: 32.8 (#58), Wizardlm 70b: —
| Benchmark | DeepSeek V4 Pro | Wizardlm 70b |
|---|---|---|
| APEX-Agents | 47.3% | — |
| Vending-Bench 2 | 3,285 | — |
Reasoning DeepSeek V4 Pro leads
DeepSeek V4 Pro: 56.5 (#24), Wizardlm 70b: 20.7 (#234)
| Benchmark | DeepSeek V4 Pro | Wizardlm 70b |
|---|---|---|
| LMArena Hard Prompts | 1461 | 1079 |
| 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% | — |
| 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 70b: 32.2 (#218)
| Benchmark | DeepSeek V4 Pro | Wizardlm 70b |
|---|---|---|
| LMArena Math | 1455 | 1116 |
| 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% | — |
Knowledge Not comparable
DeepSeek V4 Pro: 59.5 (#31), Wizardlm 70b: —
| Benchmark | DeepSeek V4 Pro | Wizardlm 70b |
|---|---|---|
| GPQA Diamond | 91.7% | — |
| SimpleQA Verified | 52.9% | — |
| Vectara Hallucination Rate | 8.6% | — |
| LMArena Expert | 1464 | — |
Multilingual DeepSeek V4 Pro leads
DeepSeek V4 Pro: 54.4 (#45), Wizardlm 70b: 29.6 (#265)
| Benchmark | DeepSeek V4 Pro | Wizardlm 70b |
|---|---|---|
| LMArena Non-English | 1439 | 1078 |
| LMArena Chinese | 1486 | 1052 |
| LMArena German | 1458 | 1083 |
| LMArena Russian | 1453 | 1155 |
| LMArena French | 1472 | — |
| LMArena Japanese | 1445 | — |
| LMArena Korean | 1447 | — |
| LMArena Spanish | 1458 | — |
Instruction Following DeepSeek V4 Pro leads
DeepSeek V4 Pro: 76.1 (#47), Wizardlm 70b: 56.3 (#273)
| Benchmark | DeepSeek V4 Pro | Wizardlm 70b |
|---|---|---|
| LMArena Instruction Following | 1448 | 1093 |
Long Context DeepSeek V4 Pro leads
DeepSeek V4 Pro: 45.0 (#51), Wizardlm 70b: 33.3 (#263)
| Benchmark | DeepSeek V4 Pro | Wizardlm 70b |
|---|---|---|
| LMArena Longer Query | 1458 | 1097 |
| CL-bench Life | 13.5% | — |
Writing & Preference DeepSeek V4 Pro leads
DeepSeek V4 Pro: 65.5 (#46), Wizardlm 70b: 34.8 (#269)
| Benchmark | DeepSeek V4 Pro | Wizardlm 70b |
|---|---|---|
| LMArena Text | 1451 | 1120 |
| LMArena Creative Writing | 1446 | 1149 |
| LMArena Multi-Turn | 1467 | 1108 |
| EQ-Bench Creative Writing | 1553 | — |
| EQ-Bench 4 | 1166 | — |
Frequently asked questions
Is DeepSeek V4 Pro better than Wizardlm 70b?
DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 33.0 on the Noometry Index.
Is DeepSeek V4 Pro or Wizardlm 70b better for coding?
DeepSeek V4 Pro scores higher on coding benchmarks: 52.4 versus 31.4 in the Noometry coding category.
How many benchmarks do DeepSeek V4 Pro and Wizardlm 70b share?
12 benchmarks have published results for both models. DeepSeek V4 Pro has 48 scored results on Noometry and Wizardlm 70b has 12.