Model comparison
C4ai Aya Expanse 8b vs GPT-4
C4ai Aya Expanse 8b is the stronger model overall, scoring 34.9 to 29.1 on the Noometry Index.
Last verified . 14 shared benchmarks.
CohereSummary
- They share 14 benchmarks with published results for both. C4ai Aya Expanse 8b scores higher in 5 categories and GPT-4 in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where C4ai Aya Expanse 8b leads 33.3 to 10.8.
- C4ai Aya Expanse 8b has downloadable open weights; the other is API-only.
Side by side
| C4ai Aya Expanse 8b | GPT-4 | |
|---|---|---|
| Provider | Cohere | OpenAI |
| Noometry Index | 34.9 | 29.1 |
| Released | — | 2023-03-14 |
| Weights | Open | Proprietary |
| Context window | — | 8K |
| Max output | — | 8K |
| Input $ / M tokens | — | $30 |
| Output $ / M tokens | — | $60 |
| Results tracked | 15 | 38 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding C4ai Aya Expanse 8b leads
C4ai Aya Expanse 8b: 33.8 (#252), GPT-4: 31.6 (#283)
| Benchmark | C4ai Aya Expanse 8b | GPT-4 |
|---|---|---|
| LMArena Coding | 1160 | 1254 |
| WeirdML | — | 12.4% |
| BigCodeBench Instruct | — | 46% |
| BigCodeBench Complete | — | 57.2% |
| HumanEval+ | — | 79.3% |
Agentic & Tool Use Not comparable
C4ai Aya Expanse 8b: —, GPT-4: —
| Benchmark | C4ai Aya Expanse 8b | GPT-4 |
|---|---|---|
| METR Time Horizons | — | 36.1% |
Reasoning C4ai Aya Expanse 8b leads
C4ai Aya Expanse 8b: 22.4 (#197), GPT-4: 17.8 (#289)
| Benchmark | C4ai Aya Expanse 8b | GPT-4 |
|---|---|---|
| LMArena Hard Prompts | 1156 | 1241 |
| Chess Puzzles | — | 4% |
| Mystery Game Puzzles | — | 12% |
| DTBench | — | 62.7% |
| LMCA | — | 17.1% |
| BIG-Bench Hard | — | 75.1% |
| Epoch Capabilities Index | — | 125.89 |
| ForecastBench | — | 57.8 |
| HellaSwag | — | 95.3% |
| WinoGrande | — | 87.5% |
Math C4ai Aya Expanse 8b leads
C4ai Aya Expanse 8b: 33.3 (#203), GPT-4: 10.8 (#309)
| Benchmark | C4ai Aya Expanse 8b | GPT-4 |
|---|---|---|
| LMArena Math | 1168 | 1269 |
| OTIS Mock AIME 2024-2025 | — | 1.1% |
| MATH Level 5 | — | 23% |
| GSM8K | — | 92% |
Knowledge C4ai Aya Expanse 8b leads
C4ai Aya Expanse 8b: 33.6 (#201), GPT-4: 18.4 (#282)
| Benchmark | C4ai Aya Expanse 8b | GPT-4 |
|---|---|---|
| LMArena Expert | 1153 | 1211 |
| GPQA Diamond | — | 35.7% |
| Vectara Hallucination Rate | 9.5% | — |
| MMLU | — | 86.4% |
| TriviaQA | — | 84.8% |
Multilingual GPT-4 leads
C4ai Aya Expanse 8b: 36.1 (#242), GPT-4: 40.6 (#215)
| Benchmark | C4ai Aya Expanse 8b | GPT-4 |
|---|---|---|
| LMArena Non-English | 1180 | 1246 |
| LMArena Chinese | 1181 | 1242 |
| LMArena German | 1188 | 1251 |
| LMArena Japanese | 1120 | 1209 |
| LMArena Russian | 1197 | 1251 |
| LMArena French | — | 1283 |
| LMArena Korean | — | 1184 |
| LMArena Spanish | — | 1261 |
Instruction Following GPT-4 leads
C4ai Aya Expanse 8b: 60.1 (#253), GPT-4: 65.3 (#222)
| Benchmark | C4ai Aya Expanse 8b | GPT-4 |
|---|---|---|
| LMArena Instruction Following | 1155 | 1241 |
Long Context GPT-4 leads
C4ai Aya Expanse 8b: 36.1 (#236), GPT-4: 37.7 (#212)
| Benchmark | C4ai Aya Expanse 8b | GPT-4 |
|---|---|---|
| LMArena Longer Query | 1191 | 1244 |
Writing & Preference C4ai Aya Expanse 8b leads
C4ai Aya Expanse 8b: 39.0 (#250), GPT-4: 34.9 (#268)
| Benchmark | C4ai Aya Expanse 8b | GPT-4 |
|---|---|---|
| LMArena Text | 1185 | 1263 |
| LMArena Creative Writing | 1168 | 1244 |
| LMArena Multi-Turn | 1160 | 1257 |
| EQ-Bench Creative Writing | — | 752 |
Frequently asked questions
Is C4ai Aya Expanse 8b better than GPT-4?
C4ai Aya Expanse 8b is the stronger model overall, scoring 34.9 to 29.1 on the Noometry Index.
Is C4ai Aya Expanse 8b or GPT-4 better for coding?
C4ai Aya Expanse 8b scores higher on coding benchmarks: 33.8 versus 31.6 in the Noometry coding category.
How many benchmarks do C4ai Aya Expanse 8b and GPT-4 share?
14 benchmarks have published results for both models. C4ai Aya Expanse 8b has 15 scored results on Noometry and GPT-4 has 38.