Skip to main content

Claude Haiku 4.5 vs Claude 3.7 Sonnet

SpecClaude Haiku 4.5Claude 3.7 Sonnet
Respan Index19.3 (#131)19.3 (#131)
Blended price per 1M$2-
Context window200K200K
Input / output per 1M$1 / $5-
Max output64K128K
Inputtext, visiontext, vision
Released2025-10-152025-02-24

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.

CategoryClaude Haiku 4.5Claude 3.7 Sonnet
Coding5.1 Claude Haiku 4.57.3 Claude 3.7 Sonnet
Agents15.8 Claude Haiku 4.513.9 Claude 3.7 Sonnet
Reasoning21.5 Claude Haiku 4.523.1 Claude 3.7 Sonnet
Knowledge & language13.2 Claude Haiku 4.515.7* Claude 3.7 Sonnet
Human preference49.1 Claude Haiku 4.544.1 Claude 3.7 Sonnet

* Estimated: no published scores in that category. How the Respan Index works

Benchmarks both report

Claude Haiku 4.5 leads on 4 of the 5 benchmarks both report. Higher is better. Each score links to where it was published.

BenchmarkClaude Haiku 4.5Claude 3.7 Sonnet
LMArena Elo14141388
GPQA Diamond71.2%79.7%
MATH Level 5 (Epoch AI)96.4%91.2%
OTIS Mock AIME 2024-2025 (Epoch AI)66.7%57.8%
SWE-bench Verified73.3%70.3%

FAQ

Is Claude Haiku 4.5 better than Claude 3.7 Sonnet?

Claude Haiku 4.5 and Claude 3.7 Sonnet tie on the Respan Index at 19.3. Claude Haiku 4.5 leads on 4 of the 5 benchmarks both report.

Which has the larger context window?

Both accept 200K tokens of context.

Compare other models

vs

Built for AI agents.
Break less.
Ship more.