Claude Haiku 5.5 vs Grok 4.7

Anthropic against xAI. Prices, scores and speed below are live.

  • Claude Haiku 5.5 costs 93% less on blended price ($0.30 against $4.50 per 1M tokens, 3 input to 1 output).
  • Claude Haiku 5.5 scores higher on the Artificial Analysis Intelligence Index: 36.5 against 35.5.
  • On the 30 benchmarks both have scores on, Claude Haiku 5.5 leads on 18 and Grok 4.7 on 11, with 1 tied.
  • Claude Haiku 5.5 reads more context: 1M tokens against 500K.
  • Claude Haiku 5.5 is newer: listed Oct 7, 2026, against Sep 21, 2026.

Side by side

Claude Haiku 5.5Grok 4.7
LabAnthropicxAI
ListedOct 7, 2026Sep 21, 2026
Input per 1M tokens$0.15$3.00
Output per 1M tokens$0.75$9.00
Cached input per 1M$0.015$0.75
Blended (3:1) per 1M$0.30$4.50
Context window1M500K
Max output128K450K
Knowledge cutoff--
Intelligence index36.535.5
Coding index--
ReasoningYesYes
Reads imagesYesYes
Tool useYesYes
Structured outputYesYes

Every benchmark both are scored on

Each model's best score per benchmark, with its source. Scores from different sources or settings are not always comparable; each links to where it was published.

BenchmarkClaude Haiku 5.5Grok 4.7
AIME98.9%Epoch AI98.1%Epoch AI
APEX-Agents56.1%Epoch AI54.6%Epoch AI
ARC-AGI-189%Epoch AI90.2%Epoch AI
ARC-AGI-261.3%Epoch AI61.4%Epoch AI
Artificial Analysis Intelligence Index36.5Artificial Analysis and OpenRouter35.5Artificial Analysis and OpenRouter
Chess Puzzles55%Epoch AI41%Epoch AI
Design Arena: 3D1333 EloDesign Arena1260 EloDesign Arena
Design Arena: Code1278 EloDesign Arena1269 EloDesign Arena
Design Arena: Data Viz1282 EloDesign Arena1228 EloDesign Arena
Design Arena: Game Dev1316 EloDesign Arena1312 EloDesign Arena
Design Arena: UI Component1275 EloDesign Arena1275 EloDesign Arena
Design Arena: Website1257 EloDesign Arena1245 EloDesign Arena
DTBench95%Epoch AI96%Epoch AI
FrontierCode46.4Epoch AI47.6Epoch AI
FrontierMath Tier 4 (v2)46.3%Epoch AI17.1%Epoch AI
FrontierMath Tiers 1-3 (v2)75.1%Epoch AI53%Epoch AI
GPQA Diamond86.7%Artificial Analysis and OpenRouter91.9%Artificial Analysis and OpenRouter
LMArena (Coding)1454 EloLMArena1425 EloLMArena
LMArena (Overall)1399 EloLMArena1398 EloLMArena
LMArena: Creative Writing1337 EloLMArena1383 EloLMArena
LMArena: Hard Prompts1420 EloLMArena1414 EloLMArena
LMArena: Longer Query1397 EloLMArena1414 EloLMArena
LMArena: Math1437 EloLMArena1437 EloLMArena
LMArena: Multi-Turn1390 EloLMArena1396 EloLMArena
LMCA51.1Epoch AI49.4Epoch AI
Mystery Game Puzzles30%Epoch AI29%Epoch AI
ProofBench89%Epoch AI26%Epoch AI
SciCode55%Epoch AI57.8%Epoch AI
SimpleQA Verified23.8%Epoch AI56%Epoch AI
tau-bench (Airline)72.8%Artificial Analysis and OpenRouter75.3%Artificial Analysis and OpenRouter

More comparisons

Where these figures come from

Prices are GenMagic's own, what the studio and the API charge, recomputed from each provider's price list every few minutes. The indices are the Artificial Analysis indices, and every benchmark score links to its source, re-read daily. Measured speed is GenMagic's own generation records, in aggregate. See Anthropic models, xAI models, every LLM's price and our sources.