Model comparison
C4ai Aya Expanse 32b vs o3
o3 is the stronger model overall, scoring 47.5 to 35.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
CohereSummary
- They share 17 benchmarks with published results for both. C4ai Aya Expanse 32b scores higher in 0 categories and o3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where o3 leads 54.6 to 33.2.
- o3 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 | o3 | |
|---|---|---|
| Provider | Cohere | OpenAI |
| Noometry Index | 35.9 | 47.5 |
| Released | 2024-10-24 | 2025-04-16 |
| Weights | Open | Proprietary |
| Context window | 128K | 200K |
| Max output | 4K | 100K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $8 |
| Results tracked | 18 | 63 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3 leads
C4ai Aya Expanse 32b: 34.8 (#231), o3: 46.8 (#64)
| Benchmark | C4ai Aya Expanse 32b | o3 |
|---|---|---|
| LMArena Coding | 1197 | 1408 |
| SWE-bench Verified | — | 62.3% |
| SWE-bench Verified (bash only) | — | 58.4% |
| Aider Polyglot | — | 81.3% |
| GSO | — | 8.8% |
| WeirdML | — | 52.4% |
| CadEval | — | 74% |
| ALE-Bench | — | 933.55 |
Agentic & Tool Use Not comparable
C4ai Aya Expanse 32b: —, o3: 34.5 (#44)
| Benchmark | C4ai Aya Expanse 32b | o3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 63% |
| GDPval | — | 30.8% |
| DeepResearch Bench | — | 45.2% |
| OSWorld | — | 23% |
| LMArena Search | — | 1144 |
| METR Time Horizons | — | 65.4% |
Reasoning o3 leads
C4ai Aya Expanse 32b: 23.3 (#180), o3: 32.0 (#78)
| Benchmark | C4ai Aya Expanse 32b | o3 |
|---|---|---|
| LMArena Hard Prompts | 1193 | 1402 |
| ARC-AGI-2 | — | 6.5% |
| SimpleBench | — | 53.1% |
| Kagi LLM Benchmark | — | 67.6% |
| ARC-AGI-1 | — | 60.8% |
| CritPt | — | 1.4% |
| Chess Puzzles | — | 38% |
| EnigmaEval | — | 13.1% |
| Mystery Game Puzzles | — | 29% |
| DTBench | — | 84.8% |
| LMCA | — | 39.7% |
| Epoch Capabilities Index | — | 146.86 |
| ForecastBench | — | 62.5 |
Math o3 leads
C4ai Aya Expanse 32b: 34.0 (#197), o3: 50.2 (#58)
| Benchmark | C4ai Aya Expanse 32b | o3 |
|---|---|---|
| LMArena Math | 1200 | 1426 |
| FrontierMath (Tiers 1-3) | — | 33.3% |
| OTIS Mock AIME 2024-2025 | — | 84.4% |
| Omni-MATH | — | 71.4% |
| MATH Level 5 | — | 97.8% |
| FrontierMath (Feb 2025 set) | — | 18.7% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge o3 leads
C4ai Aya Expanse 32b: 33.2 (#206), o3: 54.6 (#52)
| Benchmark | C4ai Aya Expanse 32b | o3 |
|---|---|---|
| LMArena Expert | 1182 | 1402 |
| GPQA Diamond | — | 81.8% |
| Humanity's Last Exam | — | 20.3% |
| SimpleQA Verified | — | 49.4% |
| MMLU-Pro | — | 85.9% |
| Confabulations | — | 14.4% |
| Vectara Hallucination Rate | 10.9% | — |
| GPQA (HELM) | — | 75.3% |
Multimodal Not comparable
C4ai Aya Expanse 32b: —, o3: 41.4 (#36)
| Benchmark | C4ai Aya Expanse 32b | o3 |
|---|---|---|
| LMArena Vision | — | 1214 |
| GeoBench | — | 74% |
| VPCT | — | 52% |
Multilingual o3 leads
C4ai Aya Expanse 32b: 38.4 (#230), o3: 51.7 (#105)
| Benchmark | C4ai Aya Expanse 32b | o3 |
|---|---|---|
| LMArena Non-English | 1213 | 1401 |
| LMArena Chinese | 1211 | 1437 |
| LMArena French | 1248 | 1430 |
| LMArena German | 1199 | 1420 |
| LMArena Japanese | 1163 | 1403 |
| LMArena Korean | 1158 | 1370 |
| LMArena Russian | 1227 | 1406 |
| LMArena Spanish | 1193 | 1395 |
Instruction Following o3 leads
C4ai Aya Expanse 32b: 62.6 (#237), o3: 72.8 (#127)
| Benchmark | C4ai Aya Expanse 32b | o3 |
|---|---|---|
| LMArena Instruction Following | 1196 | 1368 |
| IFEval | — | 86.9% |
Long Context o3 leads
C4ai Aya Expanse 32b: 37.2 (#220), o3: 53.3 (#6)
| Benchmark | C4ai Aya Expanse 32b | o3 |
|---|---|---|
| LMArena Longer Query | 1228 | 1372 |
| Fiction.LiveBench | — | 88.9% |
| CL-bench | — | 17.8% |
Writing & Preference o3 leads
C4ai Aya Expanse 32b: 42.2 (#235), o3: 63.5 (#64)
| Benchmark | C4ai Aya Expanse 32b | o3 |
|---|---|---|
| LMArena Text | 1224 | 1410 |
| LMArena Creative Writing | 1200 | 1359 |
| LMArena Multi-Turn | 1190 | 1405 |
| Short-Story Creative Writing | — | 83.9% |
| EQ-Bench Creative Writing | — | 1676 |
| WildBench | — | 86.1% |
Frequently asked questions
Is C4ai Aya Expanse 32b better than o3?
o3 is the stronger model overall, scoring 47.5 to 35.9 on the Noometry Index.
Is C4ai Aya Expanse 32b or o3 better for coding?
o3 scores higher on coding benchmarks: 46.8 versus 34.8 in the Noometry coding category.
Which has the bigger context window?
o3 does, with 200K tokens against 128K.
How many benchmarks do C4ai Aya Expanse 32b and o3 share?
17 benchmarks have published results for both models. C4ai Aya Expanse 32b has 18 scored results on Noometry and o3 has 63.