# Claude 3 Haiku vs Gemini 2.0 Flash (Feb 2025)

> Gemini 2.0 Flash (Feb 2025) is the stronger model overall, scoring 34.8 to 25.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-haiku-vs-gemini-2-0-flash
- Last updated: 2026-10-10
- Shared benchmarks: 31

## Summary

- They share 31 benchmarks with published results for both. Claude 3 Haiku scores higher in 1 category and Gemini 2.0 Flash (Feb 2025) in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 2.0 Flash (Feb 2025) leads 36.1 to 9.2.
- The biggest single-benchmark swing is MATH Level 5: 14.9% for Claude 3 Haiku and 82.2% for Gemini 2.0 Flash (Feb 2025).

## Snapshot

| | Claude 3 Haiku | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| Provider | Anthropic | Google |
| Noometry Index | 25.7 | 34.8 |
| Rank | 333 | 223 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Proprietary |

## Coding

- Claude 3 Haiku: 26.1 (#320)
- Gemini 2.0 Flash (Feb 2025): 28.2 (#308)

| Benchmark | Claude 3 Haiku | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| WeirdML | 9.8% | 25.8% |
| BigCodeBench Instruct | 39.4% | 45.9% |
| LMArena Coding | 1199 | 1351 |
| BigCodeBench Complete | 50.1% | 59.9% |
| CadEval | 12% | 30% |
| SWE-bench Verified (bash only) | — | 13.5% |
| Aider Polyglot | — | 38.2% |
| LiveBench Coding | — | 63.4% |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |

## Agentic & Tool Use

- Claude 3 Haiku: —
- Gemini 2.0 Flash (Feb 2025): 28.0 (#85)

| Benchmark | Claude 3 Haiku | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| TheAgentCompany | — | 11.4% |

## Reasoning

- Claude 3 Haiku: 15.7 (#303)
- Gemini 2.0 Flash (Feb 2025): 15.2 (#308)

| Benchmark | Claude 3 Haiku | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| Kagi LLM Benchmark | 34.2% | 37.8% |
| LMArena Hard Prompts | 1174 | 1346 |
| DTBench | 50.1% | 63.2% |
| Epoch Capabilities Index | 118.3 | 135.36 |
| ARC-AGI-2 | — | 1.3% |
| SimpleBench | — | 31.1% |
| EnigmaEval | — | 1.1% |
| LiveBench Reasoning | — | 78.2% |
| LiveBench Data Analysis | — | 69.4% |
| LMCA | 8.8% | — |
| ForecastBench | 53.2 | — |
| LiveBench | — | 66.9% |
| WinoGrande | 74.2% | — |

## Math

- Claude 3 Haiku: 9.2 (#313)
- Gemini 2.0 Flash (Feb 2025): 36.1 (#127)

| Benchmark | Claude 3 Haiku | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.8% | 57.8% |
| LMArena Math | 1188 | 1351 |
| MATH Level 5 | 14.9% | 82.2% |
| Omni-MATH | — | 45.9% |
| LiveBench Math | — | 75.8% |
| FrontierMath (Feb 2025 set) | — | 1.7% |

## Knowledge

- Claude 3 Haiku: 17.3 (#280)
- Gemini 2.0 Flash (Feb 2025): 32.0 (#207)

| Benchmark | Claude 3 Haiku | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| GPQA Diamond | 36.3% | 64.1% |
| Confabulations | 34.2% | 12.4% |
| LMArena Expert | 1148 | 1340 |
| MMLU | 73.8% | 79.7% |
| Humanity's Last Exam | — | 6.6% |
| MMLU-Pro | — | 73.7% |
| GPQA (HELM) | — | 55.6% |

## Multimodal

- Claude 3 Haiku: 23.1 (#123)
- Gemini 2.0 Flash (Feb 2025): 35.9 (#74)

| Benchmark | Claude 3 Haiku | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| LMArena Vision | 950 | 1158 |
| GeoBench | — | 77% |
| ScienceQA | 72% | — |

## Multilingual

- Claude 3 Haiku: 36.1 (#238)
- Gemini 2.0 Flash (Feb 2025): 47.6 (#144)

| Benchmark | Claude 3 Haiku | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| LMArena Non-English | 1178 | 1342 |
| LMArena Chinese | 1155 | 1373 |
| LMArena French | 1194 | 1390 |
| LMArena German | 1174 | 1354 |
| LMArena Japanese | 1102 | 1293 |
| LMArena Korean | 1108 | 1314 |
| LMArena Russian | 1204 | 1351 |
| LMArena Spanish | 1165 | 1363 |

## Instruction Following

- Claude 3 Haiku: 61.5 (#242)
- Gemini 2.0 Flash (Feb 2025): 74.6 (#91)

| Benchmark | Claude 3 Haiku | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| LMArena Instruction Following | 1174 | 1336 |
| LiveBench Instruction Following | — | 85.8% |
| IFEval | — | 84.1% |

## Long Context

- Claude 3 Haiku: 36.1 (#232)
- Gemini 2.0 Flash (Feb 2025): 38.1 (#198)

| Benchmark | Claude 3 Haiku | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| LMArena Longer Query | 1191 | 1345 |
| Fiction.LiveBench | — | 61.1% |

## Writing & Preference

- Claude 3 Haiku: 29.8 (#286)
- Gemini 2.0 Flash (Feb 2025): 49.8 (#184)

| Benchmark | Claude 3 Haiku | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| LMArena Text | 1195 | 1354 |
| LMArena Creative Writing | 1157 | 1340 |
| EQ-Bench Creative Writing | 717 | 1128 |
| LMArena Multi-Turn | 1190 | 1350 |
| Short-Story Creative Writing | — | 73.8% |
| WildBench | — | 80% |
| LiveBench Language | — | 51.3% |

## FAQ

### Is Claude 3 Haiku better than Gemini 2.0 Flash (Feb 2025)?

Gemini 2.0 Flash (Feb 2025) is the stronger model overall, scoring 34.8 to 25.7 on the Noometry Index.

### Is Claude 3 Haiku or Gemini 2.0 Flash (Feb 2025) better for coding?

Gemini 2.0 Flash (Feb 2025) scores higher on coding benchmarks: 28.2 versus 26.1 in the Noometry coding category.

### How many benchmarks do Claude 3 Haiku and Gemini 2.0 Flash (Feb 2025) share?

31 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Gemini 2.0 Flash (Feb 2025) has 54.