Model comparison
Amazon Nova Experimental Chat 12 10 vs Gemma 3 12B
Amazon Nova Experimental Chat 12 10 is the stronger model overall, scoring 42.3 to 31.8 on the Noometry Index.
Last verified . 11 shared benchmarks.
GoogleSummary
- They share 11 benchmarks with published results for both. Amazon Nova Experimental Chat 12 10 scores higher in 8 categories and Gemma 3 12B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Amazon Nova Experimental Chat 12 10 leads 36.1 to 21.0.
- Gemma 3 12B has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Experimental Chat 12 10 | Gemma 3 12B | |
|---|---|---|
| Provider | Amazon | |
| Noometry Index | 42.3 | 31.8 |
| Released | — | 2025-03-12 |
| Weights | Proprietary | Open |
| Context window | — | 131K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.05 |
| Output $ / M tokens | — | $0.15 |
| Results tracked | 12 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Amazon Nova Experimental Chat 12 10 leads
Amazon Nova Experimental Chat 12 10: 41.5 (#112), Gemma 3 12B: 31.2 (#276)
| Benchmark | Amazon Nova Experimental Chat 12 10 | Gemma 3 12B |
|---|---|---|
| LMArena Coding | 1430 | 1281 |
| SciCode | — | 17.4% |
Agentic & Tool Use Not comparable
Amazon Nova Experimental Chat 12 10: —, Gemma 3 12B: 25.3 (#101)
| Benchmark | Amazon Nova Experimental Chat 12 10 | Gemma 3 12B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 30.4% |
Reasoning Amazon Nova Experimental Chat 12 10 leads
Amazon Nova Experimental Chat 12 10: 28.1 (#93), Gemma 3 12B: 15.2 (#307)
| Benchmark | Amazon Nova Experimental Chat 12 10 | Gemma 3 12B |
|---|---|---|
| LMArena Hard Prompts | 1427 | 1309 |
| CritPt | — | 0% |
| Chess Puzzles | — | 0% |
| DTBench | — | 48.8% |
| LMCA | — | 4.5% |
| Epoch Capabilities Index | — | 123.49 |
Math Amazon Nova Experimental Chat 12 10 leads
Amazon Nova Experimental Chat 12 10: 36.1 (#130), Gemma 3 12B: 21.0 (#273)
| Benchmark | Amazon Nova Experimental Chat 12 10 | Gemma 3 12B |
|---|---|---|
| LMArena Math | 1418 | 1307 |
| OTIS Mock AIME 2024-2025 | — | 16.7% |
Knowledge Amazon Nova Experimental Chat 12 10 leads
Amazon Nova Experimental Chat 12 10: 38.6 (#133), Gemma 3 12B: 26.5 (#250)
| Benchmark | Amazon Nova Experimental Chat 12 10 | Gemma 3 12B |
|---|---|---|
| LMArena Expert | 1409 | 1248 |
| GPQA Diamond | — | 39.5% |
| Vectara Hallucination Rate | — | 4.4% |
Multimodal Not comparable
Amazon Nova Experimental Chat 12 10: —, Gemma 3 12B: —
| Benchmark | Amazon Nova Experimental Chat 12 10 | Gemma 3 12B |
|---|---|---|
| MindCube | — | 46.7% |
Multilingual Amazon Nova Experimental Chat 12 10 leads
Amazon Nova Experimental Chat 12 10: 51.7 (#103), Gemma 3 12B: 45.9 (#160)
| Benchmark | Amazon Nova Experimental Chat 12 10 | Gemma 3 12B |
|---|---|---|
| LMArena Non-English | 1399 | 1318 |
| LMArena Russian | 1397 | 1335 |
| LMArena Chinese | 1440 | — |
| LMArena German | — | 1370 |
Instruction Following Amazon Nova Experimental Chat 12 10 leads
Amazon Nova Experimental Chat 12 10: 73.4 (#117), Gemma 3 12B: 68.8 (#179)
| Benchmark | Amazon Nova Experimental Chat 12 10 | Gemma 3 12B |
|---|---|---|
| LMArena Instruction Following | 1387 | 1299 |
Long Context Amazon Nova Experimental Chat 12 10 leads
Amazon Nova Experimental Chat 12 10: 42.4 (#120), Gemma 3 12B: 40.0 (#157)
| Benchmark | Amazon Nova Experimental Chat 12 10 | Gemma 3 12B |
|---|---|---|
| LMArena Longer Query | 1391 | 1317 |
Writing & Preference Amazon Nova Experimental Chat 12 10 leads
Amazon Nova Experimental Chat 12 10: 59.7 (#104), Gemma 3 12B: 47.7 (#205)
| Benchmark | Amazon Nova Experimental Chat 12 10 | Gemma 3 12B |
|---|---|---|
| LMArena Text | 1420 | 1334 |
| LMArena Creative Writing | 1351 | 1331 |
| LMArena Multi-Turn | 1409 | 1334 |
| EQ-Bench Creative Writing | — | 1126 |
Frequently asked questions
Is Amazon Nova Experimental Chat 12 10 better than Gemma 3 12B?
Amazon Nova Experimental Chat 12 10 is the stronger model overall, scoring 42.3 to 31.8 on the Noometry Index.
Is Amazon Nova Experimental Chat 12 10 or Gemma 3 12B better for coding?
Amazon Nova Experimental Chat 12 10 scores higher on coding benchmarks: 41.5 versus 31.2 in the Noometry coding category.
How many benchmarks do Amazon Nova Experimental Chat 12 10 and Gemma 3 12B share?
11 benchmarks have published results for both models. Amazon Nova Experimental Chat 12 10 has 12 scored results on Noometry and Gemma 3 12B has 24.