Claude 4.5 Haiku (Reasoning)
AnthropicClaude
Release Date
2025-10-15
Parameters
—
Context Length
—
Modalities
—
Capability Radar
34
general
50
coding
81
reasoning
47
science
72
agents
80
multimodal
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Code Ranking | 238 | 60.0 | AA |
| General Ranking | 233 | 50.0 | AA |
| Science | 294 | 47.0 | AA |
Benchmark Scores (LLM Stats)
(LLM Stats (zeroeval))No benchmark data available
AA Evaluation Indices
(Artificial Analysis)Math Index(Artificial Analysis)83.7
Aime 25(MAA (Mathematical Association of America))83.7
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))76.0
Lcr(Artificial Analysis)74.3
Gpqa(NYU + Cohere + Anthropic (2023))67.2
Livecodebench(UC Berkeley + MIT + Cornell (2024))61.5
Tau2(Sierra + U Toronto + Vector Institute (2025))54.7
Ifbench(Google Research (2023))54.3
Terminalbench V2 144.2
Coding Index(Artificial Analysis)43.9
Scicode(UIUC + Argonne National Lab (2024))42.2
Terminalbench Hard(Stanford × Laude Institute (2026))27.3
Intelligence Index(Artificial Analysis)16.9
Hle(Center for AI Safety + Scale AI (2025))10.4
Tau Banking9.3
Terminalbench V4 00.0
LLM Stats Category Scores
(LLM Stats (zeroeval))No category score data available
Pricing
Input Price$1 / 1M tokens
Output Price$5 / 1M tokens
Blended Price (3:1)$2 / 1M tokens
Speed
Tokens/sec117.0
Time to First Token13.08s
Time to Answer13.08s
Provider Price Ranking
Provider Price Ranking
1 providers
ProviderInputOutput
1AnthropicPRIMARY
$1
$5
Compare pricing across different API providers for this model.