Model comparison
C4ai Aya Expanse 32b vs Gemini 3.8 Flash
Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 35.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
Cohere
GoogleSummary
- They share 17 benchmarks with published results for both. C4ai Aya Expanse 32b scores higher in 0 categories and Gemini 3.8 Flash in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.8 Flash leads 76.9 to 23.3.
- Gemini 3.8 Flash accepts more context: 1.05M tokens versus 128K.
- C4ai Aya Expanse 32b has downloadable open weights; the other is API-only.
Side by side
| C4ai Aya Expanse 32b | Gemini 3.8 Flash | |
|---|---|---|
| Provider | Cohere | |
| Noometry Index | 35.9 | 61.8 |
| Released | 2024-10-24 | 2026-09-02 |
| Weights | Open | Proprietary |
| Context window | 128K | 1.05M |
| Max output | 4K | 66K |
| Input $ / M tokens | — | $0.75 |
| Output $ / M tokens | — | $3.75 |
| Results tracked | 18 | 50 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.8 Flash leads
C4ai Aya Expanse 32b: 34.8 (#231), Gemini 3.8 Flash: 59.2 (#15)
| Benchmark | C4ai Aya Expanse 32b | Gemini 3.8 Flash |
|---|---|---|
| LMArena Coding | 1197 | 1510 |
| DeepSWE | — | 73.8% |
| FrontierCode | — | 41.2% |
| CursorBench | — | 39.6% |
| LMArena WebDev | — | 1584 |
| FrontierSWE | — | 19.6% |
| SciCode | — | 56.6% |
| WeirdML | — | 84.8% |
| ALE-Bench | — | 1,270 |
Agentic & Tool Use Not comparable
C4ai Aya Expanse 32b: —, Gemini 3.8 Flash: 41.8 (#21)
| Benchmark | C4ai Aya Expanse 32b | Gemini 3.8 Flash |
|---|---|---|
| APEX-Agents | — | 64.3% |
| Remote Labor Index | — | 5.8% |
| GDP.pdf | — | 23.4% |
| Vending-Bench 2 | — | 5,094 |
Reasoning Gemini 3.8 Flash leads
C4ai Aya Expanse 32b: 23.3 (#180), Gemini 3.8 Flash: 76.9 (#5)
| Benchmark | C4ai Aya Expanse 32b | Gemini 3.8 Flash |
|---|---|---|
| LMArena Hard Prompts | 1193 | 1508 |
| ARC-AGI-2 | — | 89.2% |
| NYT Connections (extended) | — | 97.4% |
| ARC-AGI-1 | — | 98.5% |
| CritPt | — | 18.3% |
| Chess Puzzles | — | 61% |
| Mystery Game Puzzles | — | 47% |
| DTBench | — | 95.7% |
| LMCA | — | 52.9% |
| Surface Evolver Bench | — | 76.9% |
| Epoch Capabilities Index | — | 156.71 |
Math Gemini 3.8 Flash leads
C4ai Aya Expanse 32b: 34.0 (#197), Gemini 3.8 Flash: 65.3 (#28)
| Benchmark | C4ai Aya Expanse 32b | Gemini 3.8 Flash |
|---|---|---|
| LMArena Math | 1200 | 1528 |
| FrontierMath (Tiers 1-3) | — | 68.4% |
| FrontierMath Tier 4 | — | 22% |
| OTIS Mock AIME 2024-2025 | — | 98.9% |
| ProofBench | — | 48% |
Knowledge Gemini 3.8 Flash leads
C4ai Aya Expanse 32b: 33.2 (#206), Gemini 3.8 Flash: 74.8 (#2)
| Benchmark | C4ai Aya Expanse 32b | Gemini 3.8 Flash |
|---|---|---|
| LMArena Expert | 1182 | 1524 |
| GPQA Diamond | — | 95.4% |
| Humanity's Last Exam | — | 44.5% |
| SimpleQA Verified | — | 69.7% |
| Vectara Hallucination Rate | 10.9% | — |
Multimodal Not comparable
C4ai Aya Expanse 32b: —, Gemini 3.8 Flash: 40.7 (#45)
| Benchmark | C4ai Aya Expanse 32b | Gemini 3.8 Flash |
|---|---|---|
| LMArena Vision | — | 1314 |
| Blueprint-Bench 2 | — | 38.6% |
| Furniture Assembly | — | 31.7% |
Multilingual Gemini 3.8 Flash leads
C4ai Aya Expanse 32b: 38.4 (#230), Gemini 3.8 Flash: 58.0 (#5)
| Benchmark | C4ai Aya Expanse 32b | Gemini 3.8 Flash |
|---|---|---|
| LMArena Non-English | 1213 | 1491 |
| LMArena Chinese | 1211 | 1554 |
| LMArena French | 1248 | 1498 |
| LMArena German | 1199 | 1493 |
| LMArena Japanese | 1163 | 1502 |
| LMArena Korean | 1158 | 1459 |
| LMArena Russian | 1227 | 1515 |
| LMArena Spanish | 1193 | 1485 |
Instruction Following Gemini 3.8 Flash leads
C4ai Aya Expanse 32b: 62.6 (#237), Gemini 3.8 Flash: 78.0 (#13)
| Benchmark | C4ai Aya Expanse 32b | Gemini 3.8 Flash |
|---|---|---|
| LMArena Instruction Following | 1196 | 1490 |
Long Context Gemini 3.8 Flash leads
C4ai Aya Expanse 32b: 37.2 (#220), Gemini 3.8 Flash: 46.3 (#24)
| Benchmark | C4ai Aya Expanse 32b | Gemini 3.8 Flash |
|---|---|---|
| LMArena Longer Query | 1228 | 1508 |
Writing & Preference Gemini 3.8 Flash leads
C4ai Aya Expanse 32b: 42.2 (#235), Gemini 3.8 Flash: 72.2 (#15)
| Benchmark | C4ai Aya Expanse 32b | Gemini 3.8 Flash |
|---|---|---|
| LMArena Text | 1224 | 1499 |
| LMArena Creative Writing | 1200 | 1492 |
| LMArena Multi-Turn | 1190 | 1501 |
| EQ-Bench Creative Writing | — | 1748 |
Frequently asked questions
Is C4ai Aya Expanse 32b better than Gemini 3.8 Flash?
Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 35.9 on the Noometry Index.
Is C4ai Aya Expanse 32b or Gemini 3.8 Flash better for coding?
Gemini 3.8 Flash scores higher on coding benchmarks: 59.2 versus 34.8 in the Noometry coding category.
Which has the bigger context window?
Gemini 3.8 Flash does, with 1.05M tokens against 128K.
How many benchmarks do C4ai Aya Expanse 32b and Gemini 3.8 Flash share?
17 benchmarks have published results for both models. C4ai Aya Expanse 32b has 18 scored results on Noometry and Gemini 3.8 Flash has 50.