Model comparison
C4ai Aya Expanse 8b vs DeepSeek V4 Pro
DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 34.9 on the Noometry Index.
Last verified . 15 shared benchmarks.
Cohere
DeepSeekSummary
- They share 15 benchmarks with published results for both. C4ai Aya Expanse 8b scores higher in 0 categories and DeepSeek V4 Pro in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4 Pro leads 56.5 to 22.4.
Side by side
| C4ai Aya Expanse 8b | DeepSeek V4 Pro | |
|---|---|---|
| Provider | Cohere | DeepSeek |
| Noometry Index | 34.9 | 54.3 |
| Released | — | 2026-04-24 |
| Weights | Open | Open |
| Context window | — | 1M |
| Max output | — | 393K |
| Input $ / M tokens | — | $0.66 |
| Output $ / M tokens | — | $1.98 |
| Results tracked | 15 | 48 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek V4 Pro leads
C4ai Aya Expanse 8b: 33.8 (#252), DeepSeek V4 Pro: 52.4 (#34)
| Benchmark | C4ai Aya Expanse 8b | DeepSeek V4 Pro |
|---|---|---|
| LMArena Coding | 1160 | 1470 |
| SWE-bench Verified | — | 77.6% |
| FrontierCode | — | 28.6% |
| LMArena WebDev | — | 1582 |
| SciCode | — | 51% |
| WeirdML | — | 66.2% |
| ALE-Bench | — | 1,403 |
Agentic & Tool Use Not comparable
C4ai Aya Expanse 8b: —, DeepSeek V4 Pro: 32.8 (#58)
| Benchmark | C4ai Aya Expanse 8b | DeepSeek V4 Pro |
|---|---|---|
| APEX-Agents | — | 47.3% |
| Vending-Bench 2 | — | 3,285 |
Reasoning DeepSeek V4 Pro leads
C4ai Aya Expanse 8b: 22.4 (#197), DeepSeek V4 Pro: 56.5 (#24)
| Benchmark | C4ai Aya Expanse 8b | DeepSeek V4 Pro |
|---|---|---|
| LMArena Hard Prompts | 1156 | 1461 |
| ARC-AGI-2 | — | 61.3% |
| Kagi LLM Benchmark | — | 53.5% |
| NYT Connections (extended) | — | 91.3% |
| ARC-AGI-1 | — | 90.5% |
| CritPt | — | 18% |
| Chess Puzzles | — | 47% |
| Mystery Game Puzzles | — | 43% |
| DTBench | — | 93.9% |
| LMCA | — | 45.5% |
| Surface Evolver Bench | — | 40% |
| Epoch Capabilities Index | — | 155.31 |
| ForecastBench | — | 56.1 |
Math DeepSeek V4 Pro leads
C4ai Aya Expanse 8b: 33.3 (#203), DeepSeek V4 Pro: 64.8 (#30)
| Benchmark | C4ai Aya Expanse 8b | DeepSeek V4 Pro |
|---|---|---|
| LMArena Math | 1168 | 1455 |
| FrontierMath (Tiers 1-3) | — | 64.6% |
| FrontierMath Tier 4 | — | 26.8% |
| MathArena Final-Answer Competitions | — | 76.6% |
| OTIS Mock AIME 2024-2025 | — | 98.6% |
| ProofBench | — | 50% |
Knowledge DeepSeek V4 Pro leads
C4ai Aya Expanse 8b: 33.6 (#201), DeepSeek V4 Pro: 59.5 (#31)
| Benchmark | C4ai Aya Expanse 8b | DeepSeek V4 Pro |
|---|---|---|
| Vectara Hallucination Rate | 9.5% | 8.6% |
| LMArena Expert | 1153 | 1464 |
| GPQA Diamond | — | 91.7% |
| SimpleQA Verified | — | 52.9% |
Multilingual DeepSeek V4 Pro leads
C4ai Aya Expanse 8b: 36.1 (#242), DeepSeek V4 Pro: 54.4 (#45)
| Benchmark | C4ai Aya Expanse 8b | DeepSeek V4 Pro |
|---|---|---|
| LMArena Non-English | 1180 | 1439 |
| LMArena Chinese | 1181 | 1486 |
| LMArena German | 1188 | 1458 |
| LMArena Japanese | 1120 | 1445 |
| LMArena Russian | 1197 | 1453 |
| LMArena French | — | 1472 |
| LMArena Korean | — | 1447 |
| LMArena Spanish | — | 1458 |
Instruction Following DeepSeek V4 Pro leads
C4ai Aya Expanse 8b: 60.1 (#253), DeepSeek V4 Pro: 76.1 (#47)
| Benchmark | C4ai Aya Expanse 8b | DeepSeek V4 Pro |
|---|---|---|
| LMArena Instruction Following | 1155 | 1448 |
Long Context DeepSeek V4 Pro leads
C4ai Aya Expanse 8b: 36.1 (#236), DeepSeek V4 Pro: 45.0 (#51)
| Benchmark | C4ai Aya Expanse 8b | DeepSeek V4 Pro |
|---|---|---|
| LMArena Longer Query | 1191 | 1458 |
| CL-bench Life | — | 13.5% |
Writing & Preference DeepSeek V4 Pro leads
C4ai Aya Expanse 8b: 39.0 (#250), DeepSeek V4 Pro: 65.5 (#46)
| Benchmark | C4ai Aya Expanse 8b | DeepSeek V4 Pro |
|---|---|---|
| LMArena Text | 1185 | 1451 |
| LMArena Creative Writing | 1168 | 1446 |
| LMArena Multi-Turn | 1160 | 1467 |
| EQ-Bench Creative Writing | — | 1553 |
| EQ-Bench 4 | — | 1166 |
Frequently asked questions
Is C4ai Aya Expanse 8b better than DeepSeek V4 Pro?
DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 34.9 on the Noometry Index.
Is C4ai Aya Expanse 8b or DeepSeek V4 Pro better for coding?
DeepSeek V4 Pro scores higher on coding benchmarks: 52.4 versus 33.8 in the Noometry coding category.
How many benchmarks do C4ai Aya Expanse 8b and DeepSeek V4 Pro share?
15 benchmarks have published results for both models. C4ai Aya Expanse 8b has 15 scored results on Noometry and DeepSeek V4 Pro has 48.