Gemini 3.0 FlashvsHaiku 4.5
Across 9 shared benchmarks, Gemini 3.0 Flash leads overall: Gemini 3.0 Flash wins 8, Haiku 4.5 wins 1, with 0 ties and an average score difference of +25.44.
Gemini 3.0 Flash
Google Deep Mind · 2025-12-17 · AI model
Haiku 4.5
Anthropic · 2025-10-15 · Multimodal model
Gemini 3.0 Flash8 wins(89%)(11%)1 winHaiku 4.5
Benchmark scores
Grouped by capability, sorted by largest gap within each. 9 shared benchmarks.
General Knowledge
Gemini 3.0 Flash 3/3| Benchmark | Gemini 3.0 Flash | Haiku 4.5 | Diff |
|---|---|---|---|
| HLE | 43.5033 / 149thinking + 使用工具 | 4.30147 / 149Normal (No Tools) | +39.20 |
| ARC-AGI-2 | 33.6026 / 58thinking | 1.3051 / 58Normal (No Tools) | +32.30 |
| GPQA Diamond | 90.4015 / 175thinking | 60.50135 / 175 |
Specs
| Field | Gemini 3.0 Flash | Haiku 4.5 |
|---|---|---|
| Publisher | Google Deep Mind | Anthropic |
| Release date | 2025-12-17 | 2025-10-15 |
| Model type | AI model | Multimodal model |
| Architecture | Dense | Dense |
| Parameters | 0.0 | 0.0 |
| Context length | 2000K | 200K |
| Max output | 65536 | 65536 |
API pricing
Prices use DataLearner records when available; missing fields are not inferred.
| Item | Gemini 3.0 Flash | Haiku 4.5 |
|---|---|---|
| Text input | 0.5 美元/100万 tokens | 1 美元 / 100万 tokens |
| Text output | 3 美元/100万 tokens | 5 美元 / 100万 tokens |
| Cache read | 0.05 美元/100万 tokens | 1.25 美元 / 100万 tokens |
| Cache write | Not public | 0.10 美元 / 100万 tokens |
Summary
- Gemini 3.0 Flashleads in:General Knowledge (3/3), Math and Reasoning (2/2), Agent Level Benchmark (1/1), Coding and Software Engineer (1/1)
- Tied in:Claw-style Agent Evaluation
On average across the 9 shared benchmarks, Gemini 3.0 Flash scores 25.44 higher.
Largest single-benchmark gap: AIME2025 — Gemini 3.0 Flash 99.70 vs Haiku 4.5 39 (+60.70).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.