# Claude 3 Haiku vs Gemini 3.8 Flash

> Gemini 3.8 Flash is the stronger model overall, scoring 59.5 to 25.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-haiku-vs-gemini-3-8-flash
- Last updated: 2026-10-10
- Shared benchmarks: 24

## Summary

- They share 24 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and Gemini 3.8 Flash in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemini 3.8 Flash leads 74.9 to 17.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.8% for Claude 3 Haiku and 98.9% for Gemini 3.8 Flash.

## Snapshot

| | Claude 3 Haiku | Gemini 3.8 Flash |
|---|---|---|
| Provider | Anthropic | Google |
| Noometry Index | 25.7 | 59.5 |
| Rank | 333 | 13 |
| Context | — | 1.05M |
| Input $/M | — | $0.75 |
| Output $/M | — | $3.75 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude 3 Haiku: 26.1 (#320)
- Gemini 3.8 Flash: 56.4 (#17)

| Benchmark | Claude 3 Haiku | Gemini 3.8 Flash |
|---|---|---|
| LMArena Coding | 1199 | 1512 |
| DeepSWE | — | 73.8% |
| FrontierCode | — | 41.2% |
| CursorBench | — | 39.6% |
| LMArena WebDev | — | 1581 |
| FrontierSWE | — | 19.6% |
| SciCode | — | 56.6% |
| WeirdML | 9.8% | — |
| BigCodeBench Instruct | 39.4% | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
| ALE-Bench | — | 1,270 |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |

## Agentic & Tool Use

- Claude 3 Haiku: —
- Gemini 3.8 Flash: 40.3 (#22)

| Benchmark | Claude 3 Haiku | Gemini 3.8 Flash |
|---|---|---|
| APEX-Agents | — | 64.3% |
| GDP.pdf | — | 23.4% |
| Vending-Bench 2 | — | 5,094 |

## Reasoning

- Claude 3 Haiku: 15.7 (#303)
- Gemini 3.8 Flash: 64.7 (#13)

| Benchmark | Claude 3 Haiku | Gemini 3.8 Flash |
|---|---|---|
| LMArena Hard Prompts | 1174 | 1506 |
| DTBench | 50.1% | 95.7% |
| LMCA | 8.8% | 52.9% |
| Epoch Capabilities Index | 118.3 | 157.13 |
| Kagi LLM Benchmark | 34.2% | — |
| NYT Connections (extended) | — | 97.4% |
| CritPt | — | 18.3% |
| Chess Puzzles | — | 61% |
| Mystery Game Puzzles | — | 47% |
| Surface Evolver Bench | — | 76.9% |
| ForecastBench | 53.2 | — |
| WinoGrande | 74.2% | — |

## Math

- Claude 3 Haiku: 9.2 (#313)
- Gemini 3.8 Flash: 65.2 (#22)

| Benchmark | Claude 3 Haiku | Gemini 3.8 Flash |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.8% | 98.9% |
| LMArena Math | 1188 | 1528 |
| FrontierMath (Tiers 1-3) | — | 68.4% |
| FrontierMath Tier 4 | — | 22% |
| ProofBench | — | 48% |
| MATH Level 5 | 14.9% | — |

## Knowledge

- Claude 3 Haiku: 17.3 (#280)
- Gemini 3.8 Flash: 74.9 (#2)

| Benchmark | Claude 3 Haiku | Gemini 3.8 Flash |
|---|---|---|
| GPQA Diamond | 36.3% | 95.4% |
| LMArena Expert | 1148 | 1529 |
| Humanity's Last Exam | — | 44.5% |
| SimpleQA Verified | — | 69.7% |
| Confabulations | 34.2% | — |
| MMLU | 73.8% | — |

## Multimodal

- Claude 3 Haiku: 23.1 (#123)
- Gemini 3.8 Flash: 40.9 (#33)

| Benchmark | Claude 3 Haiku | Gemini 3.8 Flash |
|---|---|---|
| LMArena Vision | 950 | 1312 |
| Blueprint-Bench 2 | — | 38.6% |
| Furniture Assembly | — | 31.7% |
| ScienceQA | 72% | — |

## Multilingual

- Claude 3 Haiku: 36.1 (#238)
- Gemini 3.8 Flash: 57.9 (#5)

| Benchmark | Claude 3 Haiku | Gemini 3.8 Flash |
|---|---|---|
| LMArena Non-English | 1178 | 1486 |
| LMArena Chinese | 1155 | 1547 |
| LMArena French | 1194 | 1502 |
| LMArena German | 1174 | 1470 |
| LMArena Japanese | 1102 | 1505 |
| LMArena Korean | 1108 | 1479 |
| LMArena Russian | 1204 | 1507 |
| LMArena Spanish | 1165 | 1492 |

## Instruction Following

- Claude 3 Haiku: 61.5 (#242)
- Gemini 3.8 Flash: 78.2 (#11)

| Benchmark | Claude 3 Haiku | Gemini 3.8 Flash |
|---|---|---|
| LMArena Instruction Following | 1174 | 1489 |

## Long Context

- Claude 3 Haiku: 36.1 (#232)
- Gemini 3.8 Flash: 46.2 (#23)

| Benchmark | Claude 3 Haiku | Gemini 3.8 Flash |
|---|---|---|
| LMArena Longer Query | 1191 | 1506 |

## Writing & Preference

- Claude 3 Haiku: 29.8 (#286)
- Gemini 3.8 Flash: 72.1 (#16)

| Benchmark | Claude 3 Haiku | Gemini 3.8 Flash |
|---|---|---|
| LMArena Text | 1195 | 1494 |
| LMArena Creative Writing | 1157 | 1485 |
| EQ-Bench Creative Writing | 717 | 1748 |
| LMArena Multi-Turn | 1190 | 1503 |

## FAQ

### Is Claude 3 Haiku better than Gemini 3.8 Flash?

Gemini 3.8 Flash is the stronger model overall, scoring 59.5 to 25.7 on the Noometry Index.

### Is Claude 3 Haiku or Gemini 3.8 Flash better for coding?

Gemini 3.8 Flash scores higher on coding benchmarks: 56.4 versus 26.1 in the Noometry coding category.

### How many benchmarks do Claude 3 Haiku and Gemini 3.8 Flash share?

24 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Gemini 3.8 Flash has 46.