# Claude Haiku 5.5 vs Gemini 3.8 Flash

> Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 49.5 on the Noometry Index. Claude Haiku 5.5 costs 7.5× less per token, which makes it the better buy when Gemini 3.8 Flash's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/claude-haiku-5-5-vs-gemini-3-8-flash
- Last updated: 2026-10-12
- Shared benchmarks: 9

## Summary

- They share 9 benchmarks with published results for both. Claude Haiku 5.5 scores higher in 2 categories and Gemini 3.8 Flash in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.8 Flash leads 76.9 to 35.2.
- The biggest single-benchmark swing is SimpleQA Verified: 23.8% for Claude Haiku 5.5 and 69.7% for Gemini 3.8 Flash.
- Claude Haiku 5.5 is cheaper at $0.10 / $0.50 per million input/output tokens, against $0.75 / $3.75 for Gemini 3.8 Flash.
- Gemini 3.8 Flash accepts more context: 1.05M tokens versus 1M.

## Snapshot

| | Claude Haiku 5.5 | Gemini 3.8 Flash |
|---|---|---|
| Provider | Anthropic | Google |
| Noometry Index | 49.5 | 61.8 |
| Rank | 52 | 11 |
| Context | 1M | 1.05M |
| Input $/M | $0.10 | $0.75 |
| Output $/M | $0.50 | $3.75 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Haiku 5.5: 49.2 (#50)
- Gemini 3.8 Flash: 59.2 (#15)

| Benchmark | Claude Haiku 5.5 | Gemini 3.8 Flash |
|---|---|---|
| LMArena WebDev | 1587 | 1584 |
| DeepSWE | — | 73.8% |
| FrontierCode | — | 41.2% |
| CursorBench | — | 39.6% |
| FrontierSWE | — | 19.6% |
| SciCode | — | 56.6% |
| WeirdML | — | 84.8% |
| LMArena Coding | — | 1510 |
| ALE-Bench | — | 1,270 |

## Agentic & Tool Use

- Claude Haiku 5.5: —
- Gemini 3.8 Flash: 41.8 (#21)

| Benchmark | Claude Haiku 5.5 | Gemini 3.8 Flash |
|---|---|---|
| APEX-Agents | — | 64.3% |
| Remote Labor Index | — | 5.8% |
| GDP.pdf | — | 23.4% |
| Vending-Bench 2 | — | 5,094 |

## Reasoning

- Claude Haiku 5.5: 35.2 (#69)
- Gemini 3.8 Flash: 76.9 (#5)

| Benchmark | Claude Haiku 5.5 | Gemini 3.8 Flash |
|---|---|---|
| NYT Connections (extended) | 65.7% | 97.4% |
| Mystery Game Puzzles | 30% | 47% |
| ARC-AGI-2 | — | 89.2% |
| ARC-AGI-1 | — | 98.5% |
| CritPt | — | 18.3% |
| Chess Puzzles | — | 61% |
| LMArena Hard Prompts | — | 1508 |
| DTBench | — | 95.7% |
| LMCA | — | 52.9% |
| Surface Evolver Bench | — | 76.9% |
| Epoch Capabilities Index | — | 156.71 |

## Math

- Claude Haiku 5.5: 73.6 (#18)
- Gemini 3.8 Flash: 65.3 (#28)

| Benchmark | Claude Haiku 5.5 | Gemini 3.8 Flash |
|---|---|---|
| FrontierMath (Tiers 1-3) | 75.1% | 68.4% |
| FrontierMath Tier 4 | 46.3% | 22% |
| OTIS Mock AIME 2024-2025 | 98.9% | 98.9% |
| ProofBench | — | 48% |
| LMArena Math | — | 1528 |

## Knowledge

- Claude Haiku 5.5: 50.8 (#70)
- Gemini 3.8 Flash: 74.8 (#2)

| Benchmark | Claude Haiku 5.5 | Gemini 3.8 Flash |
|---|---|---|
| GPQA Diamond | 89.6% | 95.4% |
| SimpleQA Verified | 23.8% | 69.7% |
| Humanity's Last Exam | — | 44.5% |
| LMArena Expert | — | 1524 |

## Multimodal

- Claude Haiku 5.5: 43.7 (#21)
- Gemini 3.8 Flash: 40.7 (#45)

| Benchmark | Claude Haiku 5.5 | Gemini 3.8 Flash |
|---|---|---|
| Furniture Assembly | 47.5% | 31.7% |
| LMArena Vision | — | 1314 |
| Blueprint-Bench 2 | — | 38.6% |

## Multilingual

- Claude Haiku 5.5: —
- Gemini 3.8 Flash: 58.0 (#5)

| Benchmark | Claude Haiku 5.5 | Gemini 3.8 Flash |
|---|---|---|
| LMArena Non-English | — | 1491 |
| LMArena Chinese | — | 1554 |
| LMArena French | — | 1498 |
| LMArena German | — | 1493 |
| LMArena Japanese | — | 1502 |
| LMArena Korean | — | 1459 |
| LMArena Russian | — | 1515 |
| LMArena Spanish | — | 1485 |

## Instruction Following

- Claude Haiku 5.5: —
- Gemini 3.8 Flash: 78.0 (#13)

| Benchmark | Claude Haiku 5.5 | Gemini 3.8 Flash |
|---|---|---|
| LMArena Instruction Following | — | 1490 |

## Long Context

- Claude Haiku 5.5: —
- Gemini 3.8 Flash: 46.3 (#24)

| Benchmark | Claude Haiku 5.5 | Gemini 3.8 Flash |
|---|---|---|
| LMArena Longer Query | — | 1508 |

## Writing & Preference

- Claude Haiku 5.5: —
- Gemini 3.8 Flash: 72.2 (#15)

| Benchmark | Claude Haiku 5.5 | Gemini 3.8 Flash |
|---|---|---|
| LMArena Text | — | 1499 |
| LMArena Creative Writing | — | 1492 |
| EQ-Bench Creative Writing | — | 1748 |
| LMArena Multi-Turn | — | 1501 |

## FAQ

### Is Claude Haiku 5.5 better than Gemini 3.8 Flash?

Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 49.5 on the Noometry Index. Claude Haiku 5.5 costs 7.5× less per token, which makes it the better buy when Gemini 3.8 Flash's lead doesn't matter for your workload.

### Which is cheaper, Claude Haiku 5.5 or Gemini 3.8 Flash?

Claude Haiku 5.5 is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; Gemini 3.8 Flash lists at $0.75 and $3.75.

### Is Claude Haiku 5.5 or Gemini 3.8 Flash better for coding?

Gemini 3.8 Flash scores higher on coding benchmarks: 59.2 versus 49.2 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3.8 Flash does, with 1.05M tokens against 1M.

### How many benchmarks do Claude Haiku 5.5 and Gemini 3.8 Flash share?

9 benchmarks have published results for both models. Claude Haiku 5.5 has 9 scored results on Noometry and Gemini 3.8 Flash has 50.