Model comparison
C4ai Aya Expanse 8b vs Claude Sonnet 4
Claude Sonnet 4 is the stronger model overall, scoring 40.8 to 34.9 on the Noometry Index.
Last verified . 15 shared benchmarks.
CohereSummary
- They share 15 benchmarks with published results for both. C4ai Aya Expanse 8b scores higher in 1 category and Claude Sonnet 4 in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Claude Sonnet 4 leads 57.1 to 39.0.
- C4ai Aya Expanse 8b has downloadable open weights; the other is API-only.
Side by side
| C4ai Aya Expanse 8b | Claude Sonnet 4 | |
|---|---|---|
| Provider | Cohere | Anthropic |
| Noometry Index | 34.9 | 40.8 |
| Released | — | 2025-05-22 |
| Weights | Open | Proprietary |
| Context window | — | 200K |
| Max output | — | 64K |
| Input $ / M tokens | — | $3 |
| Output $ / M tokens | — | $15 |
| Results tracked | 15 | 58 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4 leads
C4ai Aya Expanse 8b: 33.8 (#252), Claude Sonnet 4: 43.5 (#88)
| Benchmark | C4ai Aya Expanse 8b | Claude Sonnet 4 |
|---|---|---|
| LMArena Coding | 1160 | 1414 |
| SWE-bench Verified (bash only) | — | 64.9% |
| Aider Polyglot | — | 61.3% |
| SciCode | — | 40% |
| GSO | — | 4.9% |
| WeirdML | — | 46.1% |
| ALE-Bench | — | 655.35 |
Agentic & Tool Use Not comparable
C4ai Aya Expanse 8b: —, Claude Sonnet 4: 38.5 (#31)
| Benchmark | C4ai Aya Expanse 8b | Claude Sonnet 4 |
|---|---|---|
| TheAgentCompany | — | 33.1% |
| Cybench | — | 35% |
| DeepResearch Bench | — | 46.6% |
| OSWorld | — | 43.9% |
| METR Time Horizons | — | 62% |
Reasoning Too close to call
C4ai Aya Expanse 8b: 22.4 (#197), Claude Sonnet 4: 22.9 (#187)
| Benchmark | C4ai Aya Expanse 8b | Claude Sonnet 4 |
|---|---|---|
| LMArena Hard Prompts | 1156 | 1372 |
| ARC-AGI-2 | — | 5.9% |
| SimpleBench | — | 45.5% |
| Kagi LLM Benchmark | — | 73% |
| ARC-AGI-1 | — | 40% |
| CritPt | — | 0.3% |
| EnigmaEval | — | 3.1% |
| DTBench | — | 77.1% |
| LMCA | — | 29% |
| Epoch Capabilities Index | — | 141.69 |
| ForecastBench | — | 60.2 |
Math Claude Sonnet 4 leads
C4ai Aya Expanse 8b: 33.3 (#203), Claude Sonnet 4: 43.3 (#80)
| Benchmark | C4ai Aya Expanse 8b | Claude Sonnet 4 |
|---|---|---|
| LMArena Math | 1168 | 1375 |
| OTIS Mock AIME 2024-2025 | — | 71.1% |
| Omni-MATH | — | 60.2% |
| MATH Level 5 | — | 84.4% |
| FrontierMath (Feb 2025 set) | — | 4.1% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Claude Sonnet 4 leads
C4ai Aya Expanse 8b: 33.6 (#201), Claude Sonnet 4: 41.8 (#108)
| Benchmark | C4ai Aya Expanse 8b | Claude Sonnet 4 |
|---|---|---|
| Vectara Hallucination Rate | 9.5% | 10.3% |
| LMArena Expert | 1153 | 1372 |
| GPQA Diamond | — | 79.2% |
| Humanity's Last Exam | — | 7.8% |
| MMLU-Pro | — | 84.3% |
| Confabulations | — | 13.2% |
| GPQA (HELM) | — | 70.6% |
Multimodal Not comparable
C4ai Aya Expanse 8b: —, Claude Sonnet 4: 26.2 (#121)
| Benchmark | C4ai Aya Expanse 8b | Claude Sonnet 4 |
|---|---|---|
| LMArena Vision | — | 1191 |
| GeoBench | — | 37% |
| VPCT | — | 34% |
| MindCube | — | 44.8% |
Multilingual Claude Sonnet 4 leads
C4ai Aya Expanse 8b: 36.1 (#242), Claude Sonnet 4: 46.7 (#156)
| Benchmark | C4ai Aya Expanse 8b | Claude Sonnet 4 |
|---|---|---|
| LMArena Non-English | 1180 | 1333 |
| LMArena Chinese | 1181 | 1350 |
| LMArena German | 1188 | 1331 |
| LMArena Japanese | 1120 | 1302 |
| LMArena Russian | 1197 | 1355 |
| LMArena French | — | 1363 |
| LMArena Korean | — | 1291 |
| LMArena Spanish | — | 1357 |
Instruction Following Claude Sonnet 4 leads
C4ai Aya Expanse 8b: 60.1 (#253), Claude Sonnet 4: 71.7 (#145)
| Benchmark | C4ai Aya Expanse 8b | Claude Sonnet 4 |
|---|---|---|
| LMArena Instruction Following | 1155 | 1376 |
| IFEval | — | 84% |
Long Context C4ai Aya Expanse 8b leads
C4ai Aya Expanse 8b: 36.1 (#236), Claude Sonnet 4: 33.7 (#259)
| Benchmark | C4ai Aya Expanse 8b | Claude Sonnet 4 |
|---|---|---|
| LMArena Longer Query | 1191 | 1398 |
| Fiction.LiveBench | — | 46.9% |
Writing & Preference Claude Sonnet 4 leads
C4ai Aya Expanse 8b: 39.0 (#250), Claude Sonnet 4: 57.1 (#132)
| Benchmark | C4ai Aya Expanse 8b | Claude Sonnet 4 |
|---|---|---|
| LMArena Text | 1185 | 1351 |
| LMArena Creative Writing | 1168 | 1345 |
| LMArena Multi-Turn | 1160 | 1376 |
| Short-Story Creative Writing | — | 81.4% |
| EQ-Bench Creative Writing | — | 1483 |
| WildBench | — | 83.8% |
Frequently asked questions
Is C4ai Aya Expanse 8b better than Claude Sonnet 4?
Claude Sonnet 4 is the stronger model overall, scoring 40.8 to 34.9 on the Noometry Index.
Is C4ai Aya Expanse 8b or Claude Sonnet 4 better for coding?
Claude Sonnet 4 scores higher on coding benchmarks: 43.5 versus 33.8 in the Noometry coding category.
How many benchmarks do C4ai Aya Expanse 8b and Claude Sonnet 4 share?
15 benchmarks have published results for both models. C4ai Aya Expanse 8b has 15 scored results on Noometry and Claude Sonnet 4 has 58.