# Amazon Nova Experimental Chat 12 10 vs Gemini 2.5 Flash

> Amazon Nova Experimental Chat 12 10 is the stronger model overall, scoring 42.3 to 39.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/amazon-nova-experimental-chat-12-10-vs-gemini-2-5-flash
- Last updated: 2026-10-10
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. Amazon Nova Experimental Chat 12 10 scores higher in 4 categories and Gemini 2.5 Flash in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Amazon Nova Experimental Chat 12 10 leads 28.1 to 18.2.

## Snapshot

| | Amazon Nova Experimental Chat 12 10 | Gemini 2.5 Flash |
|---|---|---|
| Provider | Amazon | Google |
| Noometry Index | 42.3 | 39.0 |
| Rank | 104 | 162 |
| Context | — | 1.05M |
| Input $/M | — | $0.30 |
| Output $/M | — | $2.50 |
| Weights | Proprietary | Proprietary |

## Coding

- Amazon Nova Experimental Chat 12 10: 41.5 (#112)
- Gemini 2.5 Flash: 35.5 (#210)

| Benchmark | Amazon Nova Experimental Chat 12 10 | Gemini 2.5 Flash |
|---|---|---|
| LMArena Coding | 1430 | 1424 |
| SWE-bench Verified (bash only) | — | 28.7% |
| Aider Polyglot | — | 55.1% |
| WeirdML | — | 41.9% |
| ALE-Bench | — | 661.88 |

## Agentic & Tool Use

- Amazon Nova Experimental Chat 12 10: —
- Gemini 2.5 Flash: 30.6 (#67)

| Benchmark | Amazon Nova Experimental Chat 12 10 | Gemini 2.5 Flash |
|---|---|---|
| Terminal-Bench | — | 17.1% |
| Berkeley Function Calling Leaderboard | — | 56.2% |
| TheAgentCompany | — | 41.1% |
| BALROG | — | 33.5% |
| Vending-Bench 2 | — | 548.84 |

## Reasoning

- Amazon Nova Experimental Chat 12 10: 28.1 (#93)
- Gemini 2.5 Flash: 18.2 (#271)

| Benchmark | Amazon Nova Experimental Chat 12 10 | Gemini 2.5 Flash |
|---|---|---|
| LMArena Hard Prompts | 1427 | 1422 |
| ARC-AGI-2 | — | 2.5% |
| SimpleBench | — | 41.2% |
| Kagi LLM Benchmark | — | 56.8% |
| ARC-AGI-1 | — | 33.3% |
| CritPt | — | 1.1% |
| EnigmaEval | — | 2.7% |
| DTBench | — | 76.5% |
| LMCA | — | 27.5% |
| Epoch Capabilities Index | — | 143.04 |
| ForecastBench | — | 60.6 |

## Math

- Amazon Nova Experimental Chat 12 10: 36.1 (#130)
- Gemini 2.5 Flash: 38.1 (#87)

| Benchmark | Amazon Nova Experimental Chat 12 10 | Gemini 2.5 Flash |
|---|---|---|
| LMArena Math | 1418 | 1415 |
| OTIS Mock AIME 2024-2025 | — | 73.1% |
| Omni-MATH | — | 38.5% |
| FrontierMath (Feb 2025 set) | — | 4.8% |
| FrontierMath Tier 4 (v1) | — | 4.2% |

## Knowledge

- Amazon Nova Experimental Chat 12 10: 38.6 (#133)
- Gemini 2.5 Flash: 36.1 (#162)

| Benchmark | Amazon Nova Experimental Chat 12 10 | Gemini 2.5 Flash |
|---|---|---|
| LMArena Expert | 1409 | 1426 |
| Humanity's Last Exam | — | 12.1% |
| MMLU-Pro | — | 63.9% |
| Confabulations | — | 16.8% |
| Vectara Hallucination Rate | — | 7.8% |
| GPQA (HELM) | — | 39% |

## Multimodal

- Amazon Nova Experimental Chat 12 10: —
- Gemini 2.5 Flash: 41.2 (#31)

| Benchmark | Amazon Nova Experimental Chat 12 10 | Gemini 2.5 Flash |
|---|---|---|
| LMArena Vision | — | 1254 |
| GeoBench | — | 76% |
| VPCT | — | 46.2% |
| SpatialViz-Bench | — | 36.9% |

## Multilingual

- Amazon Nova Experimental Chat 12 10: 51.7 (#103)
- Gemini 2.5 Flash: 52.5 (#83)

| Benchmark | Amazon Nova Experimental Chat 12 10 | Gemini 2.5 Flash |
|---|---|---|
| LMArena Non-English | 1399 | 1410 |
| LMArena Chinese | 1440 | 1450 |
| LMArena Russian | 1397 | 1415 |
| LMArena French | — | 1433 |
| LMArena German | — | 1419 |
| LMArena Japanese | — | 1403 |
| LMArena Korean | — | 1385 |
| LMArena Spanish | — | 1421 |

## Instruction Following

- Amazon Nova Experimental Chat 12 10: 73.4 (#117)
- Gemini 2.5 Flash: 75.9 (#50)

| Benchmark | Amazon Nova Experimental Chat 12 10 | Gemini 2.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1387 | 1405 |
| IFEval | — | 89.8% |

## Long Context

- Amazon Nova Experimental Chat 12 10: 42.4 (#120)
- Gemini 2.5 Flash: 47.5 (#16)

| Benchmark | Amazon Nova Experimental Chat 12 10 | Gemini 2.5 Flash |
|---|---|---|
| LMArena Longer Query | 1391 | 1419 |
| Fiction.LiveBench | — | 77.8% |

## Writing & Preference

- Amazon Nova Experimental Chat 12 10: 59.7 (#104)
- Gemini 2.5 Flash: 54.0 (#153)

| Benchmark | Amazon Nova Experimental Chat 12 10 | Gemini 2.5 Flash |
|---|---|---|
| LMArena Text | 1420 | 1417 |
| LMArena Creative Writing | 1351 | 1400 |
| LMArena Multi-Turn | 1409 | 1408 |
| Short-Story Creative Writing | — | 76.5% |
| EQ-Bench Creative Writing | — | 1137 |
| WildBench | — | 81.7% |

## FAQ

### Is Amazon Nova Experimental Chat 12 10 better than Gemini 2.5 Flash?

Amazon Nova Experimental Chat 12 10 is the stronger model overall, scoring 42.3 to 39.0 on the Noometry Index.

### Is Amazon Nova Experimental Chat 12 10 or Gemini 2.5 Flash better for coding?

Amazon Nova Experimental Chat 12 10 scores higher on coding benchmarks: 41.5 versus 35.5 in the Noometry coding category.

### How many benchmarks do Amazon Nova Experimental Chat 12 10 and Gemini 2.5 Flash share?

12 benchmarks have published results for both models. Amazon Nova Experimental Chat 12 10 has 12 scored results on Noometry and Gemini 2.5 Flash has 54.