Model comparison
DeepSeek V4 Pro vs Llama 3.2 90B
DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 27.5 on the Noometry Index.
Last verified . 3 shared benchmarks.
DeepSeek
MetaSummary
- They share 3 benchmarks with published results for both. DeepSeek V4 Pro scores higher in 4 categories and Llama 3.2 90B in 0 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek V4 Pro leads 64.8 to 11.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 98.6% for DeepSeek V4 Pro and 2.6% for Llama 3.2 90B.
Side by side
| DeepSeek V4 Pro | Llama 3.2 90B | |
|---|---|---|
| Provider | DeepSeek | Meta |
| Noometry Index | 54.3 | 27.5 |
| Released | 2026-04-24 | 2024-09-24 |
| Weights | Open | Open |
| Context window | 1M | — |
| Max output | 393K | — |
| Input $ / M tokens | $0.66 | — |
| Output $ / M tokens | $1.98 | — |
| Results tracked | 48 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
DeepSeek V4 Pro: 52.4 (#34), Llama 3.2 90B: —
| Benchmark | DeepSeek V4 Pro | Llama 3.2 90B |
|---|---|---|
| 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), Llama 3.2 90B: 30.0 (#80)
| Benchmark | DeepSeek V4 Pro | Llama 3.2 90B |
|---|---|---|
| APEX-Agents | 47.3% | — |
| BALROG | — | 27.3% |
| Vending-Bench 2 | 3,285 | — |
Reasoning DeepSeek V4 Pro leads
DeepSeek V4 Pro: 56.5 (#24), Llama 3.2 90B: 21.7 (#217)
| Benchmark | DeepSeek V4 Pro | Llama 3.2 90B |
|---|---|---|
| Epoch Capabilities Index | 155.31 | 125.5 |
| 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% | — |
| EnigmaEval | — | 0.4% |
| LMArena Hard Prompts | 1461 | — |
| Mystery Game Puzzles | 43% | — |
| DTBench | 93.9% | — |
| LMCA | 45.5% | — |
| Surface Evolver Bench | 40% | — |
| ForecastBench | 56.1 | — |
Math DeepSeek V4 Pro leads
DeepSeek V4 Pro: 64.8 (#30), Llama 3.2 90B: 11.1 (#308)
| Benchmark | DeepSeek V4 Pro | Llama 3.2 90B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 98.6% | 2.6% |
| FrontierMath (Tiers 1-3) | 64.6% | — |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 76.6% | — |
| ProofBench | 50% | — |
| LMArena Math | 1455 | — |
| MATH Level 5 | — | 39.4% |
Knowledge DeepSeek V4 Pro leads
DeepSeek V4 Pro: 59.5 (#31), Llama 3.2 90B: 21.7 (#274)
| Benchmark | DeepSeek V4 Pro | Llama 3.2 90B |
|---|---|---|
| GPQA Diamond | 91.7% | 41% |
| SimpleQA Verified | 52.9% | — |
| Vectara Hallucination Rate | 8.6% | — |
| LMArena Expert | 1464 | — |
| MMLU | — | 80.3% |
Multimodal Not comparable
DeepSeek V4 Pro: —, Llama 3.2 90B: 25.4 (#124)
| Benchmark | DeepSeek V4 Pro | Llama 3.2 90B |
|---|---|---|
| LMArena Vision | — | 1000 |
| GeoBench | — | 52% |
Multilingual Not comparable
DeepSeek V4 Pro: 54.4 (#45), Llama 3.2 90B: —
| Benchmark | DeepSeek V4 Pro | Llama 3.2 90B |
|---|---|---|
| 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), Llama 3.2 90B: —
| Benchmark | DeepSeek V4 Pro | Llama 3.2 90B |
|---|---|---|
| LMArena Instruction Following | 1448 | — |
Long Context Not comparable
DeepSeek V4 Pro: 45.0 (#51), Llama 3.2 90B: —
| Benchmark | DeepSeek V4 Pro | Llama 3.2 90B |
|---|---|---|
| CL-bench Life | 13.5% | — |
| LMArena Longer Query | 1458 | — |
Writing & Preference Not comparable
DeepSeek V4 Pro: 65.5 (#46), Llama 3.2 90B: —
| Benchmark | DeepSeek V4 Pro | Llama 3.2 90B |
|---|---|---|
| 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 Llama 3.2 90B?
DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 27.5 on the Noometry Index.
How many benchmarks do DeepSeek V4 Pro and Llama 3.2 90B share?
3 benchmarks have published results for both models. DeepSeek V4 Pro has 48 scored results on Noometry and Llama 3.2 90B has 9.