Model comparison
C4ai Aya Expanse 8b vs Llama 3.1 Tulu 3 8b
C4ai Aya Expanse 8b and Llama 3.1 Tulu 3 8b score almost the same on the Noometry Index (34.9 vs 35.7), so choose on price, context window or the category you care about most.
Last verified . 11 shared benchmarks.
Cohere
Allen Institute for AI (Ai2)Summary
- They share 11 benchmarks with published results for both. C4ai Aya Expanse 8b scores higher in 2 categories and Llama 3.1 Tulu 3 8b in 5 categories; one gap is clear of the uncertainty.
Side by side
| C4ai Aya Expanse 8b | Llama 3.1 Tulu 3 8b | |
|---|---|---|
| Provider | Cohere | Allen Institute for AI (Ai2) |
| Noometry Index | 34.9 | 35.7 |
| Released | — | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 15 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
C4ai Aya Expanse 8b: 33.8 (#252), Llama 3.1 Tulu 3 8b: 34.4 (#235)
| Benchmark | C4ai Aya Expanse 8b | Llama 3.1 Tulu 3 8b |
|---|---|---|
| LMArena Coding | 1160 | 1183 |
Reasoning Too close to call
C4ai Aya Expanse 8b: 22.4 (#197), Llama 3.1 Tulu 3 8b: 22.8 (#188)
| Benchmark | C4ai Aya Expanse 8b | Llama 3.1 Tulu 3 8b |
|---|---|---|
| LMArena Hard Prompts | 1156 | 1174 |
Math Too close to call
C4ai Aya Expanse 8b: 33.3 (#203), Llama 3.1 Tulu 3 8b: 33.9 (#198)
| Benchmark | C4ai Aya Expanse 8b | Llama 3.1 Tulu 3 8b |
|---|---|---|
| LMArena Math | 1168 | 1195 |
Knowledge Not comparable
C4ai Aya Expanse 8b: 33.6 (#201), Llama 3.1 Tulu 3 8b: —
| Benchmark | C4ai Aya Expanse 8b | Llama 3.1 Tulu 3 8b |
|---|---|---|
| Vectara Hallucination Rate | 9.5% | — |
| LMArena Expert | 1153 | — |
Multilingual Too close to call
C4ai Aya Expanse 8b: 36.1 (#242), Llama 3.1 Tulu 3 8b: 35.4 (#246)
| Benchmark | C4ai Aya Expanse 8b | Llama 3.1 Tulu 3 8b |
|---|---|---|
| LMArena Non-English | 1180 | 1169 |
| LMArena Chinese | 1181 | 1176 |
| LMArena Russian | 1197 | 1193 |
| LMArena German | 1188 | — |
| LMArena Japanese | 1120 | — |
Instruction Following Llama 3.1 Tulu 3 8b leads
C4ai Aya Expanse 8b: 60.1 (#253), Llama 3.1 Tulu 3 8b: 61.3 (#246)
| Benchmark | C4ai Aya Expanse 8b | Llama 3.1 Tulu 3 8b |
|---|---|---|
| LMArena Instruction Following | 1155 | 1174 |
Long Context Too close to call
C4ai Aya Expanse 8b: 36.1 (#236), Llama 3.1 Tulu 3 8b: 35.8 (#239)
| Benchmark | C4ai Aya Expanse 8b | Llama 3.1 Tulu 3 8b |
|---|---|---|
| LMArena Longer Query | 1191 | 1181 |
Writing & Preference Too close to call
C4ai Aya Expanse 8b: 39.0 (#250), Llama 3.1 Tulu 3 8b: 39.7 (#245)
| Benchmark | C4ai Aya Expanse 8b | Llama 3.1 Tulu 3 8b |
|---|---|---|
| LMArena Text | 1185 | 1193 |
| LMArena Creative Writing | 1168 | 1182 |
| LMArena Multi-Turn | 1160 | 1154 |
Frequently asked questions
Is C4ai Aya Expanse 8b better than Llama 3.1 Tulu 3 8b?
C4ai Aya Expanse 8b and Llama 3.1 Tulu 3 8b score almost the same on the Noometry Index (34.9 vs 35.7), so choose on price, context window or the category you care about most.
Is C4ai Aya Expanse 8b or Llama 3.1 Tulu 3 8b better for coding?
They score almost the same on coding (33.8 vs 34.4); test both on your own repository before choosing.
How many benchmarks do C4ai Aya Expanse 8b and Llama 3.1 Tulu 3 8b share?
11 benchmarks have published results for both models. C4ai Aya Expanse 8b has 15 scored results on Noometry and Llama 3.1 Tulu 3 8b has 11.