LLM Comparison

Claude Haiku 5.5 vs Hy3: benchmark scores, pricing & comparison.

Side-by-side Claude Haiku 5.5 vs Hy3 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 Haiku 5.5 ranks higher (#23 vs #57) and wins 3 of 3 shared benchmarks.

Rank #23 vs #57AskClash overall scores 55.3 vs 17.7.
Pricing $0.10/$0.50 vs $0.12/$0.43Input and output token prices per 1M tokens when published.
Proprietary vs Open WeightAnthropic vs Tencent.

Claude Haiku 5.5 vs Hy3 benchmark comparison

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

MetricClaude Haiku 5.5Hy3
Overall Score55.317.7
Leaderboard Rank#23#57
ACB63.5—
AA Intelligence Index43.434.0
AutomationBench-AA35.4—
RWT—8.0
Vibe Code Bench v1.190.4—
HLE-Diamond29.611.6
GPQA—90.4
SWE-bench—78.0
FrontierCode-AA 2.034.9—
SWE-Atlas33.9—
Terminal-Bench 4.032.8—
AA-Briefcase v1.1 (Elo)1572.2947.9
EnterpriseBench: CoreCraft—41.0
Finance Agent v2.165.4—
MKA Climb WSR41.0—
Chartography—20.3
Tau2—92.7
MRCR—75.1
Input Price (per 1M tokens)$0.10$0.12
Output Price (per 1M tokens)$0.50$0.43
Context Window1M256K
Benchmarks Published126

Claude Haiku 5.5 vs Hy3 head-to-head charts

Claude Haiku 5.5 leads 3 and Hy3 leads 0 of 3 shared benchmarks. Claude Haiku 5.5 is cheaper on a defined 1M-input / 200K-output workload. Charts show only benchmarks both models publish.

Claude Haiku 5.5Hy3
Overall
55.3Claude Haiku 5.5
17.7Hy3
AA Intelligence Index
43.4Claude Haiku 5.5
34.0Hy3
HLE-Diamond
29.6Claude Haiku 5.5
11.6Hy3
AA-Briefcase v1.1 (Elo)
1572.2Claude Haiku 5.5
947.9Hy3
Claude Haiku 5.5
Input$0.10
Output$0.50
Workload$0.20
Context1M
Hy3
Input$0.12
Output$0.43
Workload$0.21
Context256K

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

More Claude Haiku 5.5 and Hy3 comparisons

Explore how Claude Haiku 5.5 and Hy3 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.