Model comparison
C4ai Aya Expanse 32b vs GPT-4.1
C4ai Aya Expanse 32b and GPT-4.1 score almost the same on the Noometry Index (35.9 vs 35.9), so choose on price, context window or the category you care about most.
Last verified . 18 shared benchmarks.
CohereSummary
- They share 18 benchmarks with published results for both. C4ai Aya Expanse 32b scores higher in 3 categories and GPT-4.1 in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GPT-4.1 leads 57.6 to 42.2.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 10.9% for C4ai Aya Expanse 32b and 5.6% for GPT-4.1.
- GPT-4.1 accepts more context: 1.05M tokens versus 128K.
- C4ai Aya Expanse 32b has downloadable open weights; the other is API-only.
Side by side
| C4ai Aya Expanse 32b | GPT-4.1 | |
|---|---|---|
| Provider | Cohere | OpenAI |
| Noometry Index | 35.9 | 35.9 |
| Released | 2024-10-24 | 2025-04-14 |
| Weights | Open | Proprietary |
| Context window | 128K | 1.05M |
| Max output | 4K | 33K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $8 |
| Results tracked | 18 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
C4ai Aya Expanse 32b: 34.8 (#231), GPT-4.1: 34.4 (#238)
| Benchmark | C4ai Aya Expanse 32b | GPT-4.1 |
|---|---|---|
| LMArena Coding | 1197 | 1391 |
| SWE-bench Verified | — | 48.5% |
| SWE-bench Verified (bash only) | — | 39.6% |
| Aider Polyglot | — | 52.4% |
| WeirdML | — | 39% |
| CadEval | — | 42% |
| ALE-Bench | — | 558.1 |
Agentic & Tool Use Not comparable
C4ai Aya Expanse 32b: —, GPT-4.1: 34.7 (#43)
| Benchmark | C4ai Aya Expanse 32b | GPT-4.1 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 54% |
Reasoning C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 23.3 (#180), GPT-4.1: 11.7 (#339)
| Benchmark | C4ai Aya Expanse 32b | GPT-4.1 |
|---|---|---|
| LMArena Hard Prompts | 1193 | 1384 |
| ARC-AGI-2 | — | 0.4% |
| SimpleBench | — | 27% |
| Kagi LLM Benchmark | — | 52.3% |
| ARC-AGI-1 | — | 5.5% |
| Chess Puzzles | — | 6% |
| EnigmaEval | — | 2.2% |
| DTBench | — | 68.3% |
| LMCA | — | 25.6% |
| Epoch Capabilities Index | — | 136.78 |
| ForecastBench | — | 61.5 |
Math C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 34.0 (#197), GPT-4.1: 22.3 (#280)
| Benchmark | C4ai Aya Expanse 32b | GPT-4.1 |
|---|---|---|
| LMArena Math | 1200 | 1370 |
| FrontierMath (Tiers 1-3) | — | 6% |
| OTIS Mock AIME 2024-2025 | — | 38.3% |
| Omni-MATH | — | 47.1% |
| MATH Level 5 | — | 83% |
| FrontierMath (Feb 2025 set) | — | 5.5% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge GPT-4.1 leads
C4ai Aya Expanse 32b: 33.2 (#206), GPT-4.1: 37.1 (#160)
| Benchmark | C4ai Aya Expanse 32b | GPT-4.1 |
|---|---|---|
| Vectara Hallucination Rate | 10.9% | 5.6% |
| LMArena Expert | 1182 | 1364 |
| GPQA Diamond | — | 66.9% |
| Humanity's Last Exam | — | 5.4% |
| SimpleQA Verified | — | 31.1% |
| MMLU-Pro | — | 81.1% |
| GPQA (HELM) | — | 65.9% |
Multimodal Not comparable
C4ai Aya Expanse 32b: —, GPT-4.1: 38.2 (#67)
| Benchmark | C4ai Aya Expanse 32b | GPT-4.1 |
|---|---|---|
| LMArena Vision | — | 1211 |
| GeoBench | — | 72% |
Multilingual GPT-4.1 leads
C4ai Aya Expanse 32b: 38.4 (#230), GPT-4.1: 49.4 (#133)
| Benchmark | C4ai Aya Expanse 32b | GPT-4.1 |
|---|---|---|
| LMArena Non-English | 1213 | 1370 |
| LMArena Chinese | 1211 | 1382 |
| LMArena French | 1248 | 1382 |
| LMArena German | 1199 | 1381 |
| LMArena Japanese | 1163 | 1319 |
| LMArena Korean | 1158 | 1339 |
| LMArena Russian | 1227 | 1377 |
| LMArena Spanish | 1193 | 1376 |
Instruction Following GPT-4.1 leads
C4ai Aya Expanse 32b: 62.6 (#237), GPT-4.1: 71.3 (#153)
| Benchmark | C4ai Aya Expanse 32b | GPT-4.1 |
|---|---|---|
| LMArena Instruction Following | 1196 | 1367 |
| IFEval | — | 83.8% |
Long Context GPT-4.1 leads
C4ai Aya Expanse 32b: 37.2 (#220), GPT-4.1: 40.0 (#163)
| Benchmark | C4ai Aya Expanse 32b | GPT-4.1 |
|---|---|---|
| LMArena Longer Query | 1228 | 1385 |
| Fiction.LiveBench | — | 63.9% |
Writing & Preference GPT-4.1 leads
C4ai Aya Expanse 32b: 42.2 (#235), GPT-4.1: 57.6 (#125)
| Benchmark | C4ai Aya Expanse 32b | GPT-4.1 |
|---|---|---|
| LMArena Text | 1224 | 1383 |
| LMArena Creative Writing | 1200 | 1363 |
| LMArena Multi-Turn | 1190 | 1398 |
| EQ-Bench Creative Writing | — | 1420 |
| WildBench | — | 85.4% |
Frequently asked questions
Is C4ai Aya Expanse 32b better than GPT-4.1?
C4ai Aya Expanse 32b and GPT-4.1 score almost the same on the Noometry Index (35.9 vs 35.9), so choose on price, context window or the category you care about most.
Is C4ai Aya Expanse 32b or GPT-4.1 better for coding?
They score almost the same on coding (34.8 vs 34.4); test both on your own repository before choosing.
Which has the bigger context window?
GPT-4.1 does, with 1.05M tokens against 128K.
How many benchmarks do C4ai Aya Expanse 32b and GPT-4.1 share?
18 benchmarks have published results for both models. C4ai Aya Expanse 32b has 18 scored results on Noometry and GPT-4.1 has 52.