LLM Comparison

Claude Sonnet 5.5 vs Claude Haiku 5.5: benchmark scores, pricing & comparison.

Side-by-side Claude Sonnet 5.5 vs Claude Haiku 5.5 comparison across SWE-bench, GPQA, HLE, Terminal-Bench, coding agent scores, token pricing, context window, and AskClash RWT. Green marks the winner on each benchmark.

Verdict: Claude Sonnet 5.5 ranks higher (#5 vs #23) and wins 11 of 11 shared benchmarks; Claude Haiku 5.5 costs less ($0.10/$0.50 vs $2.00/$10.0 per 1M tokens).

Rank #5 vs #23AskClash overall scores 80.3 vs 55.3.
Pricing $2.00/$10.0 vs $0.10/$0.50Input and output token prices per 1M tokens when published.
Proprietary vs ProprietaryAnthropic vs Anthropic.

Claude Sonnet 5.5 vs Claude Haiku 5.5 benchmark comparison

Green cells highlight the winning model for each metric. Scores are cached from the AskClash LLM leaderboard snapshot.

MetricClaude Sonnet 5.5Claude Haiku 5.5
Overall Score80.355.3
Leaderboard Rank#5#23
ACB76.663.5
AA Intelligence Index56.043.4
AutomationBench-AA71.835.4
Vibe Code Bench v1.192.490.4
HLE-Diamond53.329.6
GPQA95.6—
FrontierCode-AA 2.041.734.9
SWE-Atlas64.233.9
Terminal-Bench 4.063.632.8
AA-Briefcase v1.1 (Elo)1815.11572.2
EnterpriseBench: CoreCraft70.8—
Finance Agent v2.167.365.4
MKA Climb WSR52.041.0
GDP.pdf51.2—
Input Price (per 1M tokens)$2.00$0.10
Output Price (per 1M tokens)$10.0$0.50
Context Window1M1M
Benchmarks Published1512

Claude Sonnet 5.5 vs Claude Haiku 5.5 head-to-head charts

Claude Sonnet 5.5 leads 11 and Claude Haiku 5.5 leads 0 of 11 shared benchmarks. Claude Haiku 5.5 is cheaper on a defined 1M-input / 200K-output workload. Charts show only benchmarks both models publish.

Claude Sonnet 5.5Claude Haiku 5.5
Overall
80.3Claude Sonnet 5.5
55.3Claude Haiku 5.5
ACB
76.6Claude Sonnet 5.5
63.5Claude Haiku 5.5
AA Intelligence Index
56.0Claude Sonnet 5.5
43.4Claude Haiku 5.5
AutomationBench-AA
71.8Claude Sonnet 5.5
35.4Claude Haiku 5.5
Vibe Code Bench v1.1
92.4Claude Sonnet 5.5
90.4Claude Haiku 5.5
HLE-Diamond
53.3Claude Sonnet 5.5
29.6Claude Haiku 5.5
FrontierCode-AA 2.0
41.7Claude Sonnet 5.5
34.9Claude Haiku 5.5
SWE-Atlas
64.2Claude Sonnet 5.5
33.9Claude Haiku 5.5
Terminal-Bench 4.0
63.6Claude Sonnet 5.5
32.8Claude Haiku 5.5
AA-Briefcase v1.1 (Elo)
1815.1Claude Sonnet 5.5
1572.2Claude Haiku 5.5
Finance Agent v2.1
67.3Claude Sonnet 5.5
65.4Claude Haiku 5.5
MKA Climb WSR
52.0Claude Sonnet 5.5
41.0Claude Haiku 5.5
Claude Sonnet 5.5
Input$2.00
Output$10.0
Workload$4.00
Context1M
Claude Haiku 5.5
Input$0.10
Output$0.50
Workload$0.20
Context1M

Workload = published cost of 1M input + 200K output tokens. Open the live leaderboard for interactive compare charts.

More Claude Sonnet 5.5 and Claude Haiku 5.5 comparisons

Explore how Claude Sonnet 5.5 and Claude Haiku 5.5 stack up against other top-ranked LLMs.

How to read this comparison

Benchmark scores

Higher is better for all benchmark scores (SWE-bench, GPQA, HLE, Terminal-Bench, etc.). Green marks the model with the higher score.

Token pricing

Lower is better for input and output prices. Green marks the cheaper model per 1M tokens.

Coverage matters

Models with fewer disclosed benchmark cells may have inflated percentile scores. Check the benchmark cell count for context.

This comparison page is generated from the AskClash LLM leaderboard cache. Open the live leaderboard for real-time scores and interactive filtering.