Artificial Analysis · Intelligence Index Benchmarks, as Artificial Analysis ran them 90% GPQA Diamond 34% Humanity's Last Exam 1% Terminal-Bench 4.0 64% Terminal-Bench 2.1 49% SciCode 23% τ²-Bench Banking 79% Long context reasoning
Speed 84.5 tokens/s
First answer 1.8 s thinking included
Per 1M tokens $0.14 in · $0.56 out
Context 262K tokens Text WebDev
Overall 74th Math 39th Polish 48th Expert 60th Instruction following 70th Longer queries 72nd Hard prompts 75th Coding 76th Creative writing 82nd Multi-turn 88th
LMArena · Text 74th of 416 · 14th of 226 open models
Against list price Rating for the price
1340 1360 1380 1400 1420 1440 1460 1480 1500 1520 $0.03 $0.1 $0.3 $1 $3 $10 $30 Hy3 Muse Wonder Gemini 3.8 Flash Gemini 3.7 Flash GLM-5.3 DeepSeek V4.1 Flash Hy3 · 1,453 · $0.23 per 1M tokens ($0.13 in, $0.53 out) · 262K context
1340 1360 1380 1400 1420 1440 1460 1480 1500 1520 $0.03 $0.1 $0.3 $1 $3 $10 $30 Hy3 Muse Wonder Gemini 3.8 Flash Gemini 3.7 Flash GLM-5.3 DeepSeek V4.1 Flash Hy3 · 1,453 · $0.23 per 1M tokens ($0.13 in, $0.53 out) · 262K context
LMArena , CC BY 4.0, 15 October 2026 · prices OpenRouter , list price blended 3:1, read 19 October 2026 · Artificial Analysis , read 19 October 2026
Hy3