Model comparison
C4ai Aya Expanse 32b vs DeepSeek-R1
DeepSeek-R1 is the stronger model overall, scoring 42.3 to 35.9 on the Noometry Index.
Last verified . 18 shared benchmarks.
Cohere
DeepSeekSummary
- They share 18 benchmarks with published results for both. C4ai Aya Expanse 32b scores higher in 1 category and DeepSeek-R1 in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-R1 leads 61.4 to 42.2.
- DeepSeek-R1 accepts more context: 164K tokens versus 128K.
- C4ai Aya Expanse 32b has downloadable open weights; the other is API-only.
Side by side
| C4ai Aya Expanse 32b | DeepSeek-R1 | |
|---|---|---|
| Provider | Cohere | DeepSeek |
| Noometry Index | 35.9 | 42.3 |
| Released | 2024-10-24 | 2025-01-20 |
| Weights | Open | Proprietary |
| Context window | 128K | 164K |
| Max output | 4K | 64K |
| Input $ / M tokens | — | $0.50 |
| Output $ / M tokens | — | $2.15 |
| Results tracked | 18 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-R1 leads
C4ai Aya Expanse 32b: 34.8 (#231), DeepSeek-R1: 46.3 (#68)
| Benchmark | C4ai Aya Expanse 32b | DeepSeek-R1 |
|---|---|---|
| LMArena Coding | 1197 | 1427 |
| Aider Polyglot | — | 71.4% |
| SciCode | — | 35.7% |
| WeirdML | — | 41.6% |
| LiveBench Coding | — | 66.7% |
| ALE-Bench | — | 804.12 |
| AlgoTune | — | 1.7 |
Agentic & Tool Use Not comparable
C4ai Aya Expanse 32b: —, DeepSeek-R1: 30.7 (#75)
| Benchmark | C4ai Aya Expanse 32b | DeepSeek-R1 |
|---|---|---|
| DeepResearch Bench | — | 35.1% |
| BALROG | — | 34.9% |
| METR Time Horizons | — | 53.8% |
Reasoning C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 23.3 (#180), DeepSeek-R1: 18.6 (#278)
| Benchmark | C4ai Aya Expanse 32b | DeepSeek-R1 |
|---|---|---|
| LMArena Hard Prompts | 1193 | 1416 |
| ARC-AGI-2 | — | 1.3% |
| SimpleBench | — | 40.8% |
| Kagi LLM Benchmark | — | 69.4% |
| ARC-AGI-1 | — | 21.2% |
| CritPt | — | 1.1% |
| LiveBench Reasoning | — | 83.2% |
| LiveBench Data Analysis | — | 69.8% |
| Epoch Capabilities Index | — | 141.29 |
| ForecastBench | — | 60 |
| LiveBench | — | 71.6% |
Math DeepSeek-R1 leads
C4ai Aya Expanse 32b: 34.0 (#197), DeepSeek-R1: 43.8 (#79)
| Benchmark | C4ai Aya Expanse 32b | DeepSeek-R1 |
|---|---|---|
| LMArena Math | 1200 | 1400 |
| OTIS Mock AIME 2024-2025 | — | 66.4% |
| Omni-MATH | — | 42.4% |
| LiveBench Math | — | 80.7% |
| MATH Level 5 | — | 96.6% |
Knowledge DeepSeek-R1 leads
C4ai Aya Expanse 32b: 33.2 (#206), DeepSeek-R1: 44.5 (#87)
| Benchmark | C4ai Aya Expanse 32b | DeepSeek-R1 |
|---|---|---|
| Vectara Hallucination Rate | 10.9% | 11.3% |
| LMArena Expert | 1182 | 1394 |
| GPQA Diamond | — | 76.3% |
| MMLU-Pro | — | 79.3% |
| Confabulations | — | 12.7% |
| GPQA (HELM) | — | 66.6% |
Multilingual DeepSeek-R1 leads
C4ai Aya Expanse 32b: 38.4 (#230), DeepSeek-R1: 52.4 (#85)
| Benchmark | C4ai Aya Expanse 32b | DeepSeek-R1 |
|---|---|---|
| LMArena Non-English | 1213 | 1412 |
| LMArena Chinese | 1211 | 1442 |
| LMArena French | 1248 | 1417 |
| LMArena German | 1199 | 1404 |
| LMArena Japanese | 1163 | 1391 |
| LMArena Korean | 1158 | 1360 |
| LMArena Russian | 1227 | 1423 |
| LMArena Spanish | 1193 | 1411 |
Instruction Following DeepSeek-R1 leads
C4ai Aya Expanse 32b: 62.6 (#237), DeepSeek-R1: 72.0 (#143)
| Benchmark | C4ai Aya Expanse 32b | DeepSeek-R1 |
|---|---|---|
| LMArena Instruction Following | 1196 | 1382 |
| LiveBench Instruction Following | — | 80.5% |
| IFEval | — | 78.4% |
Long Context DeepSeek-R1 leads
C4ai Aya Expanse 32b: 37.2 (#220), DeepSeek-R1: 45.4 (#36)
| Benchmark | C4ai Aya Expanse 32b | DeepSeek-R1 |
|---|---|---|
| LMArena Longer Query | 1228 | 1391 |
| Fiction.LiveBench | — | 75% |
Writing & Preference DeepSeek-R1 leads
C4ai Aya Expanse 32b: 42.2 (#235), DeepSeek-R1: 61.4 (#88)
| Benchmark | C4ai Aya Expanse 32b | DeepSeek-R1 |
|---|---|---|
| LMArena Text | 1224 | 1428 |
| LMArena Creative Writing | 1200 | 1405 |
| LMArena Multi-Turn | 1190 | 1405 |
| Short-Story Creative Writing | — | 83% |
| EQ-Bench Creative Writing | — | 1500 |
| WildBench | — | 82.8% |
| LiveBench Language | — | 48.5% |
Frequently asked questions
Is C4ai Aya Expanse 32b better than DeepSeek-R1?
DeepSeek-R1 is the stronger model overall, scoring 42.3 to 35.9 on the Noometry Index.
Is C4ai Aya Expanse 32b or DeepSeek-R1 better for coding?
DeepSeek-R1 scores higher on coding benchmarks: 46.3 versus 34.8 in the Noometry coding category.
Which has the bigger context window?
DeepSeek-R1 does, with 164K tokens against 128K.
How many benchmarks do C4ai Aya Expanse 32b and DeepSeek-R1 share?
18 benchmarks have published results for both models. C4ai Aya Expanse 32b has 18 scored results on Noometry and DeepSeek-R1 has 52.