TAU2
Measured May 29, 2026Source
Score
0.55
Models13 1 
Claude 4.5 Haiku (Reasoning)
AnthropicAnthropicUnited States
Claude 4.5 Haiku (Reasoning) is a fast, lightweight model from Anthropic optimized for complex reasoning tasks. It combines the speed and cost-efficiency of the Haiku series with enhanced logical and analytical capabilities.
ReasoningFastCheapMultimodal
Input / 1M tokens
$1.25Output / 1M tokens
$5.00Output tokens/s
127.68First-token seconds
8.92sSupported plans
7Benchmark history
Evaluations
Terminalbench Hard
Measured May 29, 2026Source
Score
0.27
Lcr
Measured May 29, 2026Source
Score
0.7
Ifbench
Measured May 29, 2026Source
Score
0.54
Aime 25
Measured May 29, 2026Source
Score
0.84
Scicode
Measured May 29, 2026Source
Score
0.43
Livecodebench
Measured May 29, 2026Source
Score
0.62
Hle
Measured May 29, 2026Source
Score
0.1
Gpqa
Measured May 29, 2026Source
Score
0.67
Mmlu Pro
Measured May 29, 2026Source
Score
0.76
Artificial Analysis Math Index
Measured May 29, 2026Source
Score
83.7
Artificial Analysis Coding Index
Measured May 29, 2026Source
Score
32.6
Artificial Analysis Intelligence Index
Measured May 29, 2026Source
Score
37.1
Plan availability
Products and plans that support this model
Claude Code
Claude Code
Claude Code is an AI coding agent by Anthropic that works in terminal, IDEs, and Slack to help developers build, debug, and ship code. It uses Claude models (Opus 4.8, Sonnet 4.6, Haiku 4.5) to understand codebases, make multi-file edits, and generate pull requests.
User ratings
Loading ratings...
Discussion
Thinking... Make sure you are connected to GitHub server