Claude Haiku 4.5 vs Gemini 3.8 Flash
| Spec | Claude Haiku 4.5 | Gemini 3.8 Flash |
|---|---|---|
| Respan Index | 19.5 (#121) | 54.6 (#22) |
| Blended price per 1M | $2 | $0.75 |
| Context window | 200K | 1.0M |
| Input / output per 1M | $1 / $5 | $0.375 / $1.88 |
| Max output | 64K | 66K |
| Input | text, vision | text, vision, audio |
| Released | 2025-10-15 | 2026-09-02 |
Respan Index by category
Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.
| Category | Claude Haiku 4.5 | Gemini 3.8 Flash |
|---|---|---|
| Coding | 6.1 Claude Haiku 4.5 | 36.7 Gemini 3.8 Flash |
| Agents | 16.3 Claude Haiku 4.5 | 66.2 Gemini 3.8 Flash |
| Reasoning | 21.2 Claude Haiku 4.5 | 53.7 Gemini 3.8 Flash |
| Knowledge & language | 13.2 Claude Haiku 4.5 | 70.9 Gemini 3.8 Flash |
| Human preference | 48.6 Claude Haiku 4.5 | 55.8 Gemini 3.8 Flash |
Benchmarks both report
Gemini 3.8 Flash leads on 9 of the 9 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | Claude Haiku 4.5 | Gemini 3.8 Flash |
|---|---|---|
| LMArena Elo | 1414 | 1496 |
| LMArena WebDev (LMArena) | 1330 | 1583 |
| Chess Puzzles (Epoch AI) | 8% | 58% |
| GPQA Diamond | 71.2% | 95.4% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 66.7% | 98.9% |
| SAGE (Vals AI) | 31.8% | 35.1% |
| SimpleQA Verified | 13.2% | 69.7% |
| Vending-Bench 2 (Andon Labs) | 458.89 | 5093.79 |
| WeirdML (Håvard Tveit Ihle) | 45.4% | 84.8% |
FAQ
Is Claude Haiku 4.5 better than Gemini 3.8 Flash?
Gemini 3.8 Flash scores 54.6 on the Respan Index (#22), ahead of Claude Haiku 4.5 at 19.5 (#121). Gemini 3.8 Flash leads on 9 of the 9 benchmarks both report.
Which is cheaper, Claude Haiku 4.5 or Gemini 3.8 Flash?
Claude Haiku 4.5 lists at $1 input and $5 output per 1M tokens; Gemini 3.8 Flash at $0.375 and $1.88. Gemini 3.8 Flash is 2.7x cheaper per token at list price.
Which has the larger context window?
Claude Haiku 4.5 accepts 200K tokens and Gemini 3.8 Flash 1.0M tokens.