Claude 4.5 Haiku
By Anthropic · released 2025-10-15 (12 months) · 2 effort levels
1 of 2 on the frontier at launchOff the frontier todayproprietary
- Intelligence index
- 16.90
- Cost to run the AA index
- $594
- Price per 1M tokens (in / out)
- $1.00 / $5.00
Today
Where Claude 4.5 Haiku stands on the 2026-10-25 frontier
No measured level is on the frontier today.
| Level | Input modalities | Intelligence | Cost | E2E | Today | Matchup |
|---|---|---|---|---|---|---|
| Claude 4.5 Haiku (Reasoning) | Text, Image | 16.90 | $594 | 23.7s | beaten by GPT-6.1 Sol (High) | Compare |
| Claude 4.5 Haiku (Non-reasoning) | Text, Image | 15.40 | - | 6.45s | no data | Compare |
1 of 2 effort levels plotted. The remaining levels lack intelligence or benchmark cost data.
Claude 4.5 Haiku effort levelsToday's Pareto frontierEvery other model
Matchup
Compare head to head
Suggested: what beats it, its effort levels, and frontier models near its price.
- Claude 4.5 Haiku (Reasoning) vs GPT-6.1 Sol (High)
- Claude 4.5 Haiku (Reasoning) vs GPT-6.1 Sol (Xhigh)
- Claude 4.5 Haiku (Reasoning) vs Claude 4.5 Haiku (Non-reasoning)
- Claude 4.5 Haiku (Reasoning) vs MiMo-V2.6-Pro
- Claude 4.5 Haiku (Reasoning) vs GPT-6.1 Sol (Medium)
- Claude 4.5 Haiku (Reasoning) vs GPT-6.1 Sol (Max)
Launch day
What Claude 4.5 Haiku did to the frontier on 2025-10-15
Reached the frontier
Claude 4.5 Haiku (Reasoning)
Reached the frontier1 of 2
Impact (hypervolume gained)0.04
Rank, past year's releases—
Smartest level16.90
Cheapest level$594
1 of 2 effort levels plotted. The remaining levels lack intelligence or benchmark cost data.
Reached the frontierMissed itDisplaced from the old frontierFrontier the day beforeFrontier after the releaseRegion gained (impact)
Agents:
Accept: text/markdown or ?format=md returns this page as Markdown. Markdown: /releases/claude-4-5-haiku?format=md · llms.txt · agent skill