Model comparison
C4ai Aya Expanse 32b vs Claude Opus 4
Claude Opus 4 is the stronger model overall, scoring 43.1 to 35.9 on the Noometry Index.
Last verified . 18 shared benchmarks.
CohereSummary
- They share 18 benchmarks with published results for both. C4ai Aya Expanse 32b scores higher in 0 categories and Claude Opus 4 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Claude Opus 4 leads 61.2 to 42.2.
- Claude Opus 4 accepts more context: 200K tokens versus 128K.
- C4ai Aya Expanse 32b has downloadable open weights; the other is API-only.
Side by side
| C4ai Aya Expanse 32b | Claude Opus 4 | |
|---|---|---|
| Provider | Cohere | Anthropic |
| Noometry Index | 35.9 | 43.1 |
| Released | 2024-10-24 | 2025-05-22 |
| Weights | Open | Proprietary |
| Context window | 128K | 200K |
| Max output | 4K | 32K |
| Input $ / M tokens | — | $15 |
| Output $ / M tokens | — | $75 |
| Results tracked | 18 | 56 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 4 leads
C4ai Aya Expanse 32b: 34.8 (#231), Claude Opus 4: 47.2 (#62)
| Benchmark | C4ai Aya Expanse 32b | Claude Opus 4 |
|---|---|---|
| LMArena Coding | 1197 | 1442 |
| SWE-bench Verified | — | 70.7% |
| SWE-bench Verified (bash only) | — | 67.6% |
| Aider Polyglot | — | 72% |
| GSO | — | 6.9% |
| WeirdML | — | 43.7% |
| AlgoTune | — | 1.33 |
Agentic & Tool Use Not comparable
C4ai Aya Expanse 32b: —, Claude Opus 4: 34.8 (#42)
| Benchmark | C4ai Aya Expanse 32b | Claude Opus 4 |
|---|---|---|
| Cybench | — | 38% |
| DeepResearch Bench | — | 46.8% |
| LMArena Search | — | 1127 |
| METR Time Horizons | — | 63.9% |
Reasoning Claude Opus 4 leads
C4ai Aya Expanse 32b: 23.3 (#180), Claude Opus 4: 27.3 (#121)
| Benchmark | C4ai Aya Expanse 32b | Claude Opus 4 |
|---|---|---|
| LMArena Hard Prompts | 1193 | 1399 |
| ARC-AGI-2 | — | 8.6% |
| SimpleBench | — | 58.8% |
| Kagi LLM Benchmark | — | 74.3% |
| ARC-AGI-1 | — | 35.7% |
| CritPt | — | 0.3% |
| EnigmaEval | — | 5.6% |
| DTBench | — | 81.6% |
| LMCA | — | 37.4% |
| Epoch Capabilities Index | — | 142.67 |
| ForecastBench | — | 61.1 |
Math Claude Opus 4 leads
C4ai Aya Expanse 32b: 34.0 (#197), Claude Opus 4: 42.0 (#86)
| Benchmark | C4ai Aya Expanse 32b | Claude Opus 4 |
|---|---|---|
| LMArena Math | 1200 | 1390 |
| OTIS Mock AIME 2024-2025 | — | 64.4% |
| Omni-MATH | — | 61.6% |
| MATH Level 5 | — | 85% |
| FrontierMath (Feb 2025 set) | — | 4.5% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Claude Opus 4 leads
C4ai Aya Expanse 32b: 33.2 (#206), Claude Opus 4: 44.0 (#88)
| Benchmark | C4ai Aya Expanse 32b | Claude Opus 4 |
|---|---|---|
| Vectara Hallucination Rate | 10.9% | 12% |
| LMArena Expert | 1182 | 1386 |
| GPQA Diamond | — | 76.3% |
| Humanity's Last Exam | — | 10.7% |
| MMLU-Pro | — | 87.5% |
| Confabulations | — | 15.9% |
| GPQA (HELM) | — | 70.8% |
Multimodal Not comparable
C4ai Aya Expanse 32b: —, Claude Opus 4: 31.5 (#106)
| Benchmark | C4ai Aya Expanse 32b | Claude Opus 4 |
|---|---|---|
| LMArena Vision | — | 1192 |
| GeoBench | — | 49% |
| VPCT | — | 38% |
Multilingual Claude Opus 4 leads
C4ai Aya Expanse 32b: 38.4 (#230), Claude Opus 4: 48.8 (#138)
| Benchmark | C4ai Aya Expanse 32b | Claude Opus 4 |
|---|---|---|
| LMArena Non-English | 1213 | 1362 |
| LMArena Chinese | 1211 | 1386 |
| LMArena French | 1248 | 1372 |
| LMArena German | 1199 | 1391 |
| LMArena Japanese | 1163 | 1331 |
| LMArena Korean | 1158 | 1321 |
| LMArena Russian | 1227 | 1392 |
| LMArena Spanish | 1193 | 1389 |
Instruction Following Claude Opus 4 leads
C4ai Aya Expanse 32b: 62.6 (#237), Claude Opus 4: 77.1 (#28)
| Benchmark | C4ai Aya Expanse 32b | Claude Opus 4 |
|---|---|---|
| LMArena Instruction Following | 1196 | 1406 |
| IFEval | — | 91.8% |
Long Context Claude Opus 4 leads
C4ai Aya Expanse 32b: 37.2 (#220), Claude Opus 4: 39.6 (#172)
| Benchmark | C4ai Aya Expanse 32b | Claude Opus 4 |
|---|---|---|
| LMArena Longer Query | 1228 | 1422 |
| Fiction.LiveBench | — | 61.1% |
Writing & Preference Claude Opus 4 leads
C4ai Aya Expanse 32b: 42.2 (#235), Claude Opus 4: 61.2 (#89)
| Benchmark | C4ai Aya Expanse 32b | Claude Opus 4 |
|---|---|---|
| LMArena Text | 1224 | 1377 |
| LMArena Creative Writing | 1200 | 1387 |
| LMArena Multi-Turn | 1190 | 1396 |
| Short-Story Creative Writing | — | 83.6% |
| EQ-Bench Creative Writing | — | 1580 |
| WildBench | — | 85.2% |
Frequently asked questions
Is C4ai Aya Expanse 32b better than Claude Opus 4?
Claude Opus 4 is the stronger model overall, scoring 43.1 to 35.9 on the Noometry Index.
Is C4ai Aya Expanse 32b or Claude Opus 4 better for coding?
Claude Opus 4 scores higher on coding benchmarks: 47.2 versus 34.8 in the Noometry coding category.
Which has the bigger context window?
Claude Opus 4 does, with 200K tokens against 128K.
How many benchmarks do C4ai Aya Expanse 32b and Claude Opus 4 share?
18 benchmarks have published results for both models. C4ai Aya Expanse 32b has 18 scored results on Noometry and Claude Opus 4 has 56.