# Gemini 2.0 Flash (Feb 2025) vs GPT-6 Astra

> GPT-6 Astra is the stronger model overall, scoring 70.3 to 34.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-2-0-flash-vs-gpt-6-astra
- Last updated: 2026-10-10
- Shared benchmarks: 23

## Summary

- They share 23 benchmarks with published results for both. Gemini 2.0 Flash (Feb 2025) scores higher in 0 categories and GPT-6 Astra in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-6 Astra leads 85.1 to 15.2.
- The biggest single-benchmark swing is ARC-AGI-2: 1.3% for Gemini 2.0 Flash (Feb 2025) and 95% for GPT-6 Astra.

## Snapshot

| | Gemini 2.0 Flash (Feb 2025) | GPT-6 Astra |
|---|---|---|
| Provider | Google | OpenAI |
| Noometry Index | 34.8 | 70.3 |
| Rank | 223 | 1 |
| Context | — | 1.05M |
| Input $/M | — | $10 |
| Output $/M | — | $50 |
| Weights | Proprietary | Proprietary |

## Coding

- Gemini 2.0 Flash (Feb 2025): 28.2 (#308)
- GPT-6 Astra: 70.5 (#3)

| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-6 Astra |
|---|---|---|
| WeirdML | 25.8% | 93.6% |
| LMArena Coding | 1351 | 1488 |
| DeepSWE | — | 74.1% |
| FrontierCode | — | 53.3% |
| SWE-bench Verified (bash only) | 13.5% | — |
| Aider Polyglot | 38.2% | — |
| LMArena WebDev | — | 1792 |
| FrontierSWE | — | 65.5% |
| SciCode | — | 56.5% |
| BigCodeBench Instruct | 45.9% | — |
| LiveBench Coding | 63.4% | — |
| MirrorCode | — | 46.7% |
| BigCodeBench Complete | 59.9% | — |
| CadEval | 30% | — |
| ALE-Bench | — | 2,951 |

## Agentic & Tool Use

- Gemini 2.0 Flash (Feb 2025): 28.0 (#85)
- GPT-6 Astra: 52.3 (#3)

| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-6 Astra |
|---|---|---|
| APEX-Agents | — | 64.7% |
| Remote Labor Index | — | 20.8% |
| TheAgentCompany | 11.4% | — |
| BALROG | — | 68.3% |
| Vending-Bench 2 | — | 15,515 |

## Reasoning

- Gemini 2.0 Flash (Feb 2025): 15.2 (#308)
- GPT-6 Astra: 85.1 (#1)

| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-6 Astra |
|---|---|---|
| ARC-AGI-2 | 1.3% | 95% |
| LMArena Hard Prompts | 1346 | 1464 |
| DTBench | 63.2% | 97.3% |
| Epoch Capabilities Index | 135.36 | 166.6 |
| SimpleBench | 31.1% | — |
| Kagi LLM Benchmark | 37.8% | — |
| NYT Connections (extended) | — | 98.1% |
| ARC-AGI-1 | — | 98.5% |
| CritPt | — | 31.7% |
| Chess Puzzles | — | 72% |
| EnigmaEval | 1.1% | — |
| EBR-Bench | — | 76.2% |
| LiveBench Reasoning | 78.2% | — |
| Mystery Game Puzzles | — | 84% |
| LiveBench Data Analysis | 69.4% | — |
| LMCA | — | 64.4% |
| Bench to the Future 3 | — | 0.14 |
| LiveBench | 66.9% | — |

## Math

- Gemini 2.0 Flash (Feb 2025): 36.1 (#127)
- GPT-6 Astra: 93.4 (#1)

| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-6 Astra |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 100% |
| LMArena Math | 1351 | 1463 |
| FrontierMath (Tiers 1-3) | — | 93.7% |
| FrontierMath Tier 4 | — | 97.6% |
| ProofBench | — | 99% |
| Omni-MATH | 45.9% | — |
| LiveBench Math | 75.8% | — |
| MATH Level 5 | 82.2% | — |
| FrontierMath (Feb 2025 set) | 1.7% | — |
| FrontierMath Erdős | — | 2.9% |

## Knowledge

- Gemini 2.0 Flash (Feb 2025): 32.0 (#207)
- GPT-6 Astra: 75.3 (#1)

| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-6 Astra |
|---|---|---|
| GPQA Diamond | 64.1% | 95.8% |
| Humanity's Last Exam | 6.6% | 54.8% |
| LMArena Expert | 1340 | 1486 |
| SimpleQA Verified | — | 75.6% |
| MMLU-Pro | 73.7% | — |
| Confabulations | 12.4% | — |
| Vectara Hallucination Rate | — | 8.7% |
| GPQA (HELM) | 55.6% | — |
| MMLU | 79.7% | — |

## Multimodal

- Gemini 2.0 Flash (Feb 2025): 35.9 (#74)
- GPT-6 Astra: 55.1 (#3)

| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-6 Astra |
|---|---|---|
| LMArena Vision | 1158 | 1280 |
| GeoBench | 77% | — |
| Blueprint-Bench 2 | — | 49.7% |
| Furniture Assembly | — | 80% |
| LMArena Document | — | 1468 |

## Multilingual

- Gemini 2.0 Flash (Feb 2025): 47.6 (#144)
- GPT-6 Astra: 54.0 (#53)

| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-6 Astra |
|---|---|---|
| LMArena Non-English | 1342 | 1431 |
| LMArena Chinese | 1373 | 1495 |
| LMArena French | 1390 | 1467 |
| LMArena Russian | 1351 | 1434 |
| LMArena Spanish | 1363 | 1412 |
| LMArena German | 1354 | — |
| LMArena Japanese | 1293 | — |
| LMArena Korean | 1314 | — |

## Instruction Following

- Gemini 2.0 Flash (Feb 2025): 74.6 (#91)
- GPT-6 Astra: 76.6 (#37)

| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-6 Astra |
|---|---|---|
| LMArena Instruction Following | 1336 | 1454 |
| LiveBench Instruction Following | 85.8% | — |
| IFEval | 84.1% | — |

## Long Context

- Gemini 2.0 Flash (Feb 2025): 38.1 (#198)
- GPT-6 Astra: 44.7 (#57)

| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-6 Astra |
|---|---|---|
| LMArena Longer Query | 1345 | 1460 |
| Fiction.LiveBench | 61.1% | — |

## Writing & Preference

- Gemini 2.0 Flash (Feb 2025): 49.8 (#184)
- GPT-6 Astra: 75.7 (#7)

| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-6 Astra |
|---|---|---|
| LMArena Text | 1354 | 1443 |
| LMArena Creative Writing | 1340 | 1423 |
| EQ-Bench Creative Writing | 1128 | 2173 |
| LMArena Multi-Turn | 1350 | 1457 |
| Short-Story Creative Writing | 73.8% | — |
| WildBench | 80% | — |
| LiveBench Language | 51.3% | — |

## FAQ

### Is Gemini 2.0 Flash (Feb 2025) better than GPT-6 Astra?

GPT-6 Astra is the stronger model overall, scoring 70.3 to 34.8 on the Noometry Index.

### Is Gemini 2.0 Flash (Feb 2025) or GPT-6 Astra better for coding?

GPT-6 Astra scores higher on coding benchmarks: 70.5 versus 28.2 in the Noometry coding category.

### How many benchmarks do Gemini 2.0 Flash (Feb 2025) and GPT-6 Astra share?

23 benchmarks have published results for both models. Gemini 2.0 Flash (Feb 2025) has 54 scored results on Noometry and GPT-6 Astra has 51.