Model comparison
Claude Opus 4.6 vs Llama 3.2 90B
Claude Opus 4.6 is the stronger model overall, scoring 58.3 to 27.1 on the Noometry Index.
Last verified . 5 shared benchmarks.
MetaSummary
- They share 5 benchmarks with published results for both. Claude Opus 4.6 scores higher in 5 categories and Llama 3.2 90B in 0 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Opus 4.6 leads 62.7 to 10.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 94.4% for Claude Opus 4.6 and 2.6% for Llama 3.2 90B.
- Llama 3.2 90B has downloadable open weights; the other is API-only.
Side by side
| Claude Opus 4.6 | Llama 3.2 90B | |
|---|---|---|
| Provider | Anthropic | Meta |
| Noometry Index | 58.3 | 27.1 |
| Released | 2026-02-04 | 2024-09-24 |
| Weights | Proprietary | Open |
| Context window | 1M | — |
| Max output | 128K | — |
| Input $ / M tokens | $5 | — |
| Output $ / M tokens | $25 | — |
| Results tracked | 68 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Claude Opus 4.6: 57.7 (#15), Llama 3.2 90B: —
| Benchmark | Claude Opus 4.6 | Llama 3.2 90B |
|---|---|---|
| SWE-bench Verified | 78.7% | — |
| FrontierCode | 26.6% | — |
| SWE-bench Verified (bash only) | 75.6% | — |
| LMArena WebDev | 1546 | — |
| SWE-bench Multilingual | 72% | — |
| GSO | 41.2% | — |
| WeirdML | 78% | — |
| LMArena Coding | 1535 | — |
| ALE-Bench | 996.5 | — |
| AlgoTune | 1.47 | — |
Agentic & Tool Use Claude Opus 4.6 leads
Claude Opus 4.6: 51.0 (#4), Llama 3.2 90B: 29.7 (#73)
| Benchmark | Claude Opus 4.6 | Llama 3.2 90B |
|---|---|---|
| Terminal-Bench | 79.8% | — |
| APEX-Agents | 46.3% | — |
| Remote Labor Index | 4.2% | — |
| τ²-bench Banking | 27.3% | — |
| Cybench | 93% | — |
| DeepResearch Bench | 55.3% | — |
| BALROG | — | 27.3% |
| GBAEval | 44.1% | — |
| LMArena Search | 1253 | — |
| METR Time Horizons | 78.9% | — |
| Vending-Bench 2 | 8,018 | — |
Reasoning Claude Opus 4.6 leads
Claude Opus 4.6: 57.7 (#21), Llama 3.2 90B: 20.9 (#207)
| Benchmark | Claude Opus 4.6 | Llama 3.2 90B |
|---|---|---|
| EnigmaEval | 7.6% | 0.4% |
| Epoch Capabilities Index | 155.36 | 125.5 |
| ARC-AGI-2 | 69.2% | — |
| SimpleBench | 67.6% | — |
| Kagi LLM Benchmark | 83.6% | — |
| NYT Connections (extended) | 92.1% | — |
| ARC-AGI-1 | 94% | — |
| Chess Puzzles | 17% | — |
| Thematic Generalization | 80.6% | — |
| EBR-Bench | 12.7% | — |
| LMArena Hard Prompts | 1527 | — |
| Mystery Game Puzzles | 25% | — |
| DTBench | 91.2% | — |
| LMCA | 55.8% | — |
| ForecastBench | 60 | — |
Math Claude Opus 4.6 leads
Claude Opus 4.6: 62.7 (#25), Llama 3.2 90B: 10.4 (#302)
| Benchmark | Claude Opus 4.6 | Llama 3.2 90B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 94.4% | 2.6% |
| FrontierMath (Tiers 1-3) | 66% | — |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 78.5% | — |
| ProofBench | 50% | — |
| LMArena Math | 1517 | — |
| MATH Level 5 | — | 39.4% |
| FrontierMath (Feb 2025 set) | 40.7% | — |
| FrontierMath Tier 4 (v1) | 22.9% | — |
Knowledge Claude Opus 4.6 leads
Claude Opus 4.6: 61.8 (#23), Llama 3.2 90B: 21.7 (#269)
| Benchmark | Claude Opus 4.6 | Llama 3.2 90B |
|---|---|---|
| GPQA Diamond | 90.5% | 41% |
| Humanity's Last Exam | 34.4% | — |
| SimpleQA Verified | 47% | — |
| Vectara Hallucination Rate | 12.2% | — |
| LMArena Expert | 1546 | — |
| MMLU | — | 80.3% |
Multimodal Claude Opus 4.6 leads
Claude Opus 4.6: 37.0 (#67), Llama 3.2 90B: 24.9 (#119)
| Benchmark | Claude Opus 4.6 | Llama 3.2 90B |
|---|---|---|
| LMArena Vision | 1316 | 1000 |
| GeoBench | — | 52% |
| Furniture Assembly | 28.3% | — |
| LMArena Document | 1507 | — |
Multilingual Not comparable
Claude Opus 4.6: 58.2 (#4), Llama 3.2 90B: —
| Benchmark | Claude Opus 4.6 | Llama 3.2 90B |
|---|---|---|
| LMArena Non-English | 1490 | — |
| LMArena Chinese | 1551 | — |
| LMArena French | 1513 | — |
| LMArena German | 1504 | — |
| LMArena Japanese | 1484 | — |
| LMArena Korean | 1465 | — |
| LMArena Russian | 1497 | — |
| LMArena Spanish | 1512 | — |
Instruction Following Not comparable
Claude Opus 4.6: 79.7 (#3), Llama 3.2 90B: —
| Benchmark | Claude Opus 4.6 | Llama 3.2 90B |
|---|---|---|
| LMArena Instruction Following | 1523 | — |
Long Context Not comparable
Claude Opus 4.6: 48.1 (#13), Llama 3.2 90B: —
| Benchmark | Claude Opus 4.6 | Llama 3.2 90B |
|---|---|---|
| CL-bench | 20.7% | — |
| CL-bench Life | 17% | — |
| LMArena Longer Query | 1520 | — |
Writing & Preference Not comparable
Claude Opus 4.6: 73.7 (#9), Llama 3.2 90B: —
| Benchmark | Claude Opus 4.6 | Llama 3.2 90B |
|---|---|---|
| LMArena Text | 1504 | — |
| LMArena Creative Writing | 1506 | — |
| EQ-Bench Creative Writing | 1809 | — |
| EQ-Bench 4 | 1223 | — |
| LMArena Multi-Turn | 1514 | — |
Frequently asked questions
Is Claude Opus 4.6 better than Llama 3.2 90B?
Claude Opus 4.6 is the stronger model overall, scoring 58.3 to 27.1 on the Noometry Index.
How many benchmarks do Claude Opus 4.6 and Llama 3.2 90B share?
5 benchmarks have published results for both models. Claude Opus 4.6 has 68 scored results on Noometry and Llama 3.2 90B has 9.