# Claude Haiku 4.5 vs Gemini 3.5 Flash-Lite

> Side-by-side benchmark comparison for Claude Haiku 4.5 and Gemini 3.5 Flash-Lite across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/claude-haiku-4-5-vs-gemini-3-5-flash-lite
- Last updated: September 29, 2026

- Shared sourced benchmarks: 5
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.7

## Quick Verdict

Pick Gemini 3.5 Flash-Lite if you want the stronger benchmark profile. Claude Haiku 4.5 only makes more sense when its price, context window, or workload-specific category wins matter more than the overall score.

## Summary

- Gemini 3.5 Flash-Lite leads overall 50.85 to 42.47.
- The clearest category separation is in coding, where the averages are 19.6 for Claude Haiku 4.5 and 38.5 for Gemini 3.5 Flash-Lite.
- The biggest single benchmark swing is LiveCodeBench (Vals) in Coding, with scores of 41.2% and 79.0%.
- Gemini 3.5 Flash-Lite is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.
- Gemini 3.5 Flash-Lite also has the larger context window at 1M.

## Model Snapshot

| Property | Claude Haiku 4.5 | Gemini 3.5 Flash-Lite |
|----------|----------|----------|
| Creator | Anthropic | Google |
| Type | Proprietary | Proprietary |
| Reasoning | Non-Reasoning | Reasoning |
| Context | 200K | 1M |
| Overall Score | 42.47 | 50.85 |
| Benchmarks Covered | 10 | 10 |
| Pricing (input/output) | $1.00 / $5.00 | $0.30 / $2.50 |

## Category Breakdown

### Agentic

- Winner: Gemini 3.5 Flash-Lite
- Claude Haiku 4.5 public-lane score: 22 (Supported · #96/117)
- Gemini 3.5 Flash-Lite public-lane score: 34.4 (Supported · #70/117)

| Benchmark | Claude Haiku 4.5 | Gemini 3.5 Flash-Lite | Winner |
|-----------|-----------|-----------|--------|
| JobBench | 16.0% | Coming soon | Coming soon |
| Terminal-Bench 2.1 (Vals) | 43.8% | 50.2% | Gemini 3.5 Flash-Lite |
| Terminal-Bench 2.1 | Coming soon | 54.0% | Coming soon |
| OSWorld-Verified | Coming soon | 74% | Coming soon |

### Coding

- Winner: Gemini 3.5 Flash-Lite
- Claude Haiku 4.5 public-lane score: 19.6 (Supported · #124/143)
- Gemini 3.5 Flash-Lite public-lane score: 38.5 (Supported · #68/143)

| Benchmark | Claude Haiku 4.5 | Gemini 3.5 Flash-Lite | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 73.3% | Coming soon | Coming soon |
| VulcanBench v3 | 76.2% | Coming soon | Coming soon |
| LiveCodeBench (Vals) | 41.2% | 79.0% | Gemini 3.5 Flash-Lite |
| SWE-bench (Vals) | 66.6% | 75.0% | Gemini 3.5 Flash-Lite |
| Terminal-Bench 2.1 | Coming soon | 54.0% | Coming soon |
| SWE-bench Pro | Coming soon | 54.2% | Coming soon |

### Reasoning

- Winner: Not comparable
- Claude Haiku 4.5 public-lane score: Coming soon
- Gemini 3.5 Flash-Lite public-lane score: 62.2 (#20/27)

| Benchmark | Claude Haiku 4.5 | Gemini 3.5 Flash-Lite | Winner |
|-----------|-----------|-----------|--------|
| MRCRv2 | Coming soon | 72.2% | Coming soon |

### Multimodal & Grounded

- Winner: Not comparable
- Claude Haiku 4.5 public-lane score: Coming soon
- Gemini 3.5 Flash-Lite public-lane score: 77.5 (#17/50)

### Knowledge

- Winner: Directional only
- Claude Haiku 4.5 public-lane score: 34.8 (Estimated · #119/169)
- Gemini 3.5 Flash-Lite public-lane score: 47.9 (Supported · #70/169)

| Benchmark | Claude Haiku 4.5 | Gemini 3.5 Flash-Lite | Winner |
|-----------|-----------|-----------|--------|
| GPQA Diamond (Vals) | 72.2% | 83.8% | Gemini 3.5 Flash-Lite |
| MMLU-Pro (Vals) | 78.7% | 85.8% | Gemini 3.5 Flash-Lite |

### Mathematics

- Winner: Not comparable
- Claude Haiku 4.5 public-lane score: 28.8 (Unranked · 2 rankable rows)
- Gemini 3.5 Flash-Lite public-lane score: Coming soon

| Benchmark | Claude Haiku 4.5 | Gemini 3.5 Flash-Lite | Winner |
|-----------|-----------|-----------|--------|
| FrontierMath v2 (Tiers 1-3) | 5.903% | Coming soon | Coming soon |
| FrontierMath v2 (Tier 4) | 2.083% | Coming soon | Coming soon |

## FAQ

### Which is better overall, Claude Haiku 4.5 or Gemini 3.5 Flash-Lite?

Gemini 3.5 Flash-Lite is ahead overall on BenchLM right now.

### Where is the biggest gap between Claude Haiku 4.5 and Gemini 3.5 Flash-Lite?

The widest category gap is in coding, where the averages are 19.6 for Claude Haiku 4.5 and 38.5 for Gemini 3.5 Flash-Lite.

### How many benchmarks does Claude Haiku 4.5 cover on BenchLM?

Claude Haiku 4.5 currently has 10 sourced benchmark scores on BenchLM.

### How many benchmarks does Gemini 3.5 Flash-Lite cover on BenchLM?

Gemini 3.5 Flash-Lite currently has 10 sourced benchmark scores on BenchLM.

## Related Comparisons

- [Claude Haiku 4.5 vs Claude Haiku 4.5 Thinking](/compare/claude-haiku-4-5-vs-claude-haiku-4-5-thinking)
- [Gemini 3.5 Flash-Lite vs Claude Haiku 4.5 Thinking](/compare/claude-haiku-4-5-thinking-vs-gemini-3-5-flash-lite)
- [Claude Haiku 4.5 vs GPT-6 Astra](/compare/claude-haiku-4-5-vs-gpt-6-astra)
- [Gemini 3.5 Flash-Lite vs GPT-6 Astra](/compare/gemini-3-5-flash-lite-vs-gpt-6-astra)

## Explore More

- [Claude Haiku 4.5 profile](/models/claude-haiku-4-5)
- [Gemini 3.5 Flash-Lite profile](/models/gemini-3-5-flash-lite)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)