# Claude Haiku 4.5 vs Gemini 1.5 Flash (May 2024)

> Claude Haiku 4.5 is the stronger model overall, scoring 39.5 to 33.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-haiku-4-5-vs-gemini-1-5-flash
- Last updated: 2026-10-12
- Shared benchmarks: 31

## Summary

- They share 31 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 8 categories and Gemini 1.5 Flash (May 2024) in 2 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Haiku 4.5 leads 44.9 to 22.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 66.7% for Claude Haiku 4.5 and 16.3% for Gemini 1.5 Flash (May 2024).

## Snapshot

| | Claude Haiku 4.5 | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| Provider | Anthropic | Google |
| Noometry Index | 39.5 | 33.2 |
| Rank | 165 | 246 |
| Context | 200K | — |
| Input $/M | $1 | — |
| Output $/M | $5 | — |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Haiku 4.5: 44.0 (#78)
- Gemini 1.5 Flash (May 2024): 34.4 (#236)

| Benchmark | Claude Haiku 4.5 | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| WeirdML | 45.4% | 24.9% |
| LMArena Coding | 1453 | 1261 |
| SWE-bench Verified (bash only) | 66.6% | — |
| LMArena WebDev | 1330 | — |
| SWE-bench Multilingual | 64.7% | — |
| SciCode | 43.3% | — |
| BigCodeBench Instruct | — | 43.5% |
| BigCodeBench Complete | — | 55.1% |
| ALE-Bench | 653.48 | — |
| HumanEval+ | — | 75.6% |
| MBPP+ | — | 67.5% |

## Agentic & Tool Use

- Claude Haiku 4.5: 33.6 (#52)
- Gemini 1.5 Flash (May 2024): 26.6 (#102)

| Benchmark | Claude Haiku 4.5 | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| BALROG | 31.2% | 14.6% |
| Terminal-Bench | 35.5% | — |
| Berkeley Function Calling Leaderboard | 68.7% | — |
| DeepResearch Bench | 45.5% | — |
| ExploitBench | 13.7% | — |
| Vending-Bench 2 | 458.89 | — |

## Reasoning

- Claude Haiku 4.5: 15.1 (#320)
- Gemini 1.5 Flash (May 2024): 21.7 (#215)

| Benchmark | Claude Haiku 4.5 | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| LMArena Hard Prompts | 1420 | 1257 |
| DTBench | 73.6% | 53.8% |
| Epoch Capabilities Index | 142.41 | 129.36 |
| ForecastBench | 61.4 | 53.9 |
| ARC-AGI-2 | 4% | — |
| NYT Connections (extended) | 14.3% | — |
| ARC-AGI-1 | 47.7% | — |
| CritPt | 0% | — |
| Chess Puzzles | 8% | — |
| LMCA | 30.9% | — |
| PIQA | — | 87.5% |

## Math

- Claude Haiku 4.5: 44.9 (#78)
- Gemini 1.5 Flash (May 2024): 22.1 (#281)

| Benchmark | Claude Haiku 4.5 | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 66.7% | 16.3% |
| Omni-MATH | 56.1% | 30.4% |
| LMArena Math | 1396 | 1269 |
| MATH Level 5 | 96.4% | 61.9% |
| FrontierMath (Feb 2025 set) | 5.9% | 0% |
| FrontierMath Tier 4 (v1) | 2.1% | — |
| GSM8K | — | 82.4% |

## Knowledge

- Claude Haiku 4.5: 37.7 (#153)
- Gemini 1.5 Flash (May 2024): 26.2 (#260)

| Benchmark | Claude Haiku 4.5 | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| GPQA Diamond | 71.2% | 47.3% |
| MMLU-Pro | 77.7% | 67.8% |
| GPQA (HELM) | 60.5% | 43.7% |
| LMArena Expert | 1442 | 1233 |
| SimpleQA Verified | 13.2% | — |
| Vectara Hallucination Rate | 9.8% | — |
| BoolQ | — | 85.8% |
| MMLU | — | 77.9% |

## Multimodal

- Claude Haiku 4.5: 26.8 (#118)
- Gemini 1.5 Flash (May 2024): 36.0 (#81)

| Benchmark | Claude Haiku 4.5 | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| LMArena Vision | — | 1141 |
| Video-MME | — | 70.3% |
| GeoBench | — | 76% |
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1420 | — |

## Multilingual

- Claude Haiku 4.5: 49.9 (#129)
- Gemini 1.5 Flash (May 2024): 42.9 (#189)

| Benchmark | Claude Haiku 4.5 | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| LMArena Non-English | 1377 | 1278 |
| LMArena Chinese | 1417 | 1295 |
| LMArena French | 1408 | 1258 |
| LMArena German | 1375 | 1262 |
| LMArena Japanese | 1339 | 1252 |
| LMArena Korean | 1347 | 1221 |
| LMArena Russian | 1381 | 1288 |
| LMArena Spanish | 1420 | 1243 |

## Instruction Following

- Claude Haiku 4.5: 71.4 (#149)
- Gemini 1.5 Flash (May 2024): 66.8 (#205)

| Benchmark | Claude Haiku 4.5 | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| IFEval | 80.1% | 83.1% |
| LMArena Instruction Following | 1414 | 1258 |

## Long Context

- Claude Haiku 4.5: 43.6 (#92)
- Gemini 1.5 Flash (May 2024): 39.0 (#187)

| Benchmark | Claude Haiku 4.5 | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| LMArena Longer Query | 1427 | 1284 |

## Writing & Preference

- Claude Haiku 4.5: 57.9 (#123)
- Gemini 1.5 Flash (May 2024): 48.7 (#196)

| Benchmark | Claude Haiku 4.5 | Gemini 1.5 Flash (May 2024) |
|---|---|---|
| LMArena Text | 1396 | 1287 |
| LMArena Creative Writing | 1372 | 1285 |
| WildBench | 83.9% | 79.2% |
| LMArena Multi-Turn | 1409 | 1253 |
| EQ-Bench 4 | 1064 | — |

## FAQ

### Is Claude Haiku 4.5 better than Gemini 1.5 Flash (May 2024)?

Claude Haiku 4.5 is the stronger model overall, scoring 39.5 to 33.2 on the Noometry Index.

### Is Claude Haiku 4.5 or Gemini 1.5 Flash (May 2024) better for coding?

Claude Haiku 4.5 scores higher on coding benchmarks: 44.0 versus 34.4 in the Noometry coding category.

### How many benchmarks do Claude Haiku 4.5 and Gemini 1.5 Flash (May 2024) share?

31 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and Gemini 1.5 Flash (May 2024) has 42.