Model comparison
C4ai Aya Expanse 32b vs GPT-5-Codex
GPT-5-Codex is the stronger model overall, scoring 37.3 to 35.3 on the Noometry Index.
Last verified . 0 shared benchmarks.
CohereSummary
- The widest gap is in reasoning, where GPT-5-Codex leads 30.0 to 22.3.
- GPT-5-Codex accepts more context: 400K tokens versus 128K.
- C4ai Aya Expanse 32b has downloadable open weights; the other is API-only.
Side by side
| C4ai Aya Expanse 32b | GPT-5-Codex | |
|---|---|---|
| Provider | Cohere | OpenAI |
| Noometry Index | 35.3 | 37.3 |
| Released | 2024-10-24 | 2025-09-15 |
| Weights | Open | Proprietary |
| Context window | 128K | 400K |
| Max output | 4K | 128K |
| Input $ / M tokens | — | $1.25 |
| Output $ / M tokens | — | $10 |
| Results tracked | 18 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5-Codex leads
C4ai Aya Expanse 32b: 34.3 (#227), GPT-5-Codex: 41.9 (#100)
| Benchmark | C4ai Aya Expanse 32b | GPT-5-Codex |
|---|---|---|
| WeirdML | — | 54.5% |
| LMArena Coding | 1197 | — |
Agentic & Tool Use Not comparable
C4ai Aya Expanse 32b: —, GPT-5-Codex: 30.8 (#66)
| Benchmark | C4ai Aya Expanse 32b | GPT-5-Codex |
|---|---|---|
| Terminal-Bench | — | 44.3% |
Reasoning GPT-5-Codex leads
C4ai Aya Expanse 32b: 22.3 (#183), GPT-5-Codex: 30.0 (#80)
| Benchmark | C4ai Aya Expanse 32b | GPT-5-Codex |
|---|---|---|
| Kagi LLM Benchmark | — | 70.3% |
| LMArena Hard Prompts | 1193 | — |
Math Not comparable
C4ai Aya Expanse 32b: 31.4 (#195), GPT-5-Codex: —
| Benchmark | C4ai Aya Expanse 32b | GPT-5-Codex |
|---|---|---|
| LMArena Math | 1200 | — |
Knowledge Not comparable
C4ai Aya Expanse 32b: 32.6 (#202), GPT-5-Codex: —
| Benchmark | C4ai Aya Expanse 32b | GPT-5-Codex |
|---|---|---|
| Vectara Hallucination Rate | 10.9% | — |
| LMArena Expert | 1182 | — |
Multilingual Not comparable
C4ai Aya Expanse 32b: 38.5 (#225), GPT-5-Codex: —
| Benchmark | C4ai Aya Expanse 32b | GPT-5-Codex |
|---|---|---|
| LMArena Non-English | 1213 | — |
| LMArena Chinese | 1210 | — |
| LMArena French | 1247 | — |
| LMArena German | 1199 | — |
| LMArena Japanese | 1163 | — |
| LMArena Korean | 1158 | — |
| LMArena Russian | 1227 | — |
| LMArena Spanish | 1193 | — |
Instruction Following Not comparable
C4ai Aya Expanse 32b: 62.9 (#232), GPT-5-Codex: —
| Benchmark | C4ai Aya Expanse 32b | GPT-5-Codex |
|---|---|---|
| LMArena Instruction Following | 1196 | — |
Long Context Not comparable
C4ai Aya Expanse 32b: 37.2 (#215), GPT-5-Codex: —
| Benchmark | C4ai Aya Expanse 32b | GPT-5-Codex |
|---|---|---|
| LMArena Longer Query | 1228 | — |
Writing & Preference Not comparable
C4ai Aya Expanse 32b: 42.4 (#230), GPT-5-Codex: —
| Benchmark | C4ai Aya Expanse 32b | GPT-5-Codex |
|---|---|---|
| LMArena Text | 1224 | — |
| LMArena Creative Writing | 1200 | — |
| LMArena Multi-Turn | 1190 | — |
Frequently asked questions
Is C4ai Aya Expanse 32b better than GPT-5-Codex?
GPT-5-Codex is the stronger model overall, scoring 37.3 to 35.3 on the Noometry Index.
Is C4ai Aya Expanse 32b or GPT-5-Codex better for coding?
GPT-5-Codex scores higher on coding benchmarks: 41.9 versus 34.3 in the Noometry coding category.
Which has the bigger context window?
GPT-5-Codex does, with 400K tokens against 128K.
How many benchmarks do C4ai Aya Expanse 32b and GPT-5-Codex share?
0 benchmarks have published results for both models. C4ai Aya Expanse 32b has 18 scored results on Noometry and GPT-5-Codex has 3.