Model comparison
Claude Opus 4.8 vs Olmo 3 32b Think
Claude Opus 4.8 is the stronger model overall, scoring 60.7 to 38.1 on the Noometry Index.
Last verified . 14 shared benchmarks.
Allen Institute for AI (Ai2)Summary
- They share 14 benchmarks with published results for both. Claude Opus 4.8 scores higher in 8 categories and Olmo 3 32b Think in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Opus 4.8 leads 78.2 to 33.8.
- Olmo 3 32b Think has downloadable open weights; the other is API-only.
Side by side
| Claude Opus 4.8 | Olmo 3 32b Think | |
|---|---|---|
| Provider | Anthropic | Allen Institute for AI (Ai2) |
| Noometry Index | 60.7 | 38.1 |
| Released | 2026-05-28 | — |
| Weights | Proprietary | Open |
| Context window | 1M | — |
| Max output | 128K | — |
| Input $ / M tokens | $5 | — |
| Output $ / M tokens | $25 | — |
| Results tracked | 65 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 4.8 leads
Claude Opus 4.8: 60.2 (#9), Olmo 3 32b Think: 38.0 (#169)
| Benchmark | Claude Opus 4.8 | Olmo 3 32b Think |
|---|---|---|
| LMArena Coding | 1491 | 1318 |
| DeepSWE | 59% | — |
| FrontierCode | 46.5% | — |
| LMArena WebDev | 1556 | — |
| SciCode | 53.5% | — |
| GSO | 47.1% | — |
| WeirdML | 82.9% | — |
| ALE-Bench | 1,564 | — |
Agentic & Tool Use Not comparable
Claude Opus 4.8: 47.6 (#10), Olmo 3 32b Think: —
| Benchmark | Claude Opus 4.8 | Olmo 3 32b Think |
|---|---|---|
| APEX-Agents | 48.9% | — |
| OSWorld 2.0 | 20.6% | — |
| Remote Labor Index | 8.3% | — |
| τ²-bench Banking | 39.7% | — |
| DeepResearch Bench | 50.2% | — |
| PostTrainBench | 33.8% | — |
| GBAEval | 70.9% | — |
| GDP.pdf | 24% | — |
| LMArena Search | 1204 | — |
| Vending-Bench 2 | 5,787 | — |
Reasoning Claude Opus 4.8 leads
Claude Opus 4.8: 64.6 (#14), Olmo 3 32b Think: 24.9 (#138)
| Benchmark | Claude Opus 4.8 | Olmo 3 32b Think |
|---|---|---|
| LMArena Hard Prompts | 1481 | 1302 |
| ARC-AGI-2 | 72.1% | — |
| SimpleBench | 64.8% | — |
| Kagi LLM Benchmark | 88.8% | — |
| NYT Connections (extended) | 91.1% | — |
| ARC-AGI-1 | 92.5% | — |
| CritPt | 20.9% | — |
| Chess Puzzles | 34% | — |
| EnigmaEval | 23.5% | — |
| EBR-Bench | 28.6% | — |
| Mystery Game Puzzles | 36% | — |
| DTBench | 94.9% | — |
| LMCA | 57.5% | — |
| Surface Evolver Bench | 87.5% | — |
| Bench to the Future 3 | 0.14 | — |
| Epoch Capabilities Index | 158.3 | — |
| ForecastBench | 59.9 | — |
Math Claude Opus 4.8 leads
Claude Opus 4.8: 78.2 (#11), Olmo 3 32b Think: 33.8 (#165)
| Benchmark | Claude Opus 4.8 | Olmo 3 32b Think |
|---|---|---|
| LMArena Math | 1487 | 1315 |
| FrontierMath (Tiers 1-3) | 80% | — |
| FrontierMath Tier 4 | 56.1% | — |
| MathArena Final-Answer Competitions | 91.8% | — |
| OTIS Mock AIME 2024-2025 | 98.3% | — |
| ProofBench | 69% | — |
| FrontierMath (Feb 2025 set) | 47.2% | — |
| FrontierMath Tier 4 (v1) | 31.3% | — |
Knowledge Claude Opus 4.8 leads
Claude Opus 4.8: 61.3 (#26), Olmo 3 32b Think: 34.4 (#189)
| Benchmark | Claude Opus 4.8 | Olmo 3 32b Think |
|---|---|---|
| LMArena Expert | 1501 | 1272 |
| GPQA Diamond | 91% | — |
| SimpleQA Verified | 53% | — |
Multimodal Not comparable
Claude Opus 4.8: 43.2 (#20), Olmo 3 32b Think: —
| Benchmark | Claude Opus 4.8 | Olmo 3 32b Think |
|---|---|---|
| LMArena Vision | 1295 | — |
| Blueprint-Bench 2 | 14.5% | — |
| Furniture Assembly | 42.5% | — |
| LMArena Document | 1475 | — |
Multilingual Claude Opus 4.8 leads
Claude Opus 4.8: 55.4 (#31), Olmo 3 32b Think: 41.4 (#205)
| Benchmark | Claude Opus 4.8 | Olmo 3 32b Think |
|---|---|---|
| LMArena Non-English | 1450 | 1255 |
| LMArena Chinese | 1509 | 1300 |
| LMArena French | 1482 | 1291 |
| LMArena German | 1470 | 1290 |
| LMArena Russian | 1476 | 1255 |
| LMArena Japanese | 1440 | — |
| LMArena Korean | 1432 | — |
| LMArena Spanish | 1470 | — |
Instruction Following Claude Opus 4.8 leads
Claude Opus 4.8: 77.6 (#22), Olmo 3 32b Think: 67.4 (#193)
| Benchmark | Claude Opus 4.8 | Olmo 3 32b Think |
|---|---|---|
| LMArena Instruction Following | 1476 | 1275 |
Long Context Claude Opus 4.8 leads
Claude Opus 4.8: 45.4 (#37), Olmo 3 32b Think: 39.4 (#177)
| Benchmark | Claude Opus 4.8 | Olmo 3 32b Think |
|---|---|---|
| LMArena Longer Query | 1482 | 1296 |
Writing & Preference Claude Opus 4.8 leads
Claude Opus 4.8: 72.1 (#17), Olmo 3 32b Think: 49.2 (#188)
| Benchmark | Claude Opus 4.8 | Olmo 3 32b Think |
|---|---|---|
| LMArena Text | 1460 | 1300 |
| LMArena Creative Writing | 1453 | 1256 |
| LMArena Multi-Turn | 1476 | 1289 |
| EQ-Bench Creative Writing | 1840 | — |
| EQ-Bench 4 | 1281 | — |
Frequently asked questions
Is Claude Opus 4.8 better than Olmo 3 32b Think?
Claude Opus 4.8 is the stronger model overall, scoring 60.7 to 38.1 on the Noometry Index.
Is Claude Opus 4.8 or Olmo 3 32b Think better for coding?
Claude Opus 4.8 scores higher on coding benchmarks: 60.2 versus 38.0 in the Noometry coding category.
How many benchmarks do Claude Opus 4.8 and Olmo 3 32b Think share?
14 benchmarks have published results for both models. Claude Opus 4.8 has 65 scored results on Noometry and Olmo 3 32b Think has 14.