Skip to content

Rankings

Output tokens per second

Performance measure
#ModelTokens per secondAgainst the leaderProvider
1Claude Opus 5Anthropic7.0k t/sDeepinfra
2GPT-5 NanoOpenAI5.3k t/sOpenAI
3GPT-5 NanoOpenAI5.0k t/sOpenAI
4Gemini Flash-Lite LatestGoogle4.6k t/sgoogle-aistudio
5Gemini 3.1 Pro Preview Custom ToolsGoogle4.5k t/sgoogle-aistudio
6Gemini 3.5 FlashGoogle2.2k t/sgoogle-aistudio
7gpt-oss-120b-UltraOpenAI1.6k t/sDeepinfra
8Gemini 3.1 Flash LiteGoogle1.0k t/sgoogle-aistudio
9Gemini Flash LatestGoogle900.0 t/sgoogle-aistudio
10GPT-5 MiniOpenAI696.7 t/sOpenAI
Source 
Hopscotch catalogue
Window 
24 hours
Ranked 
195 of 195 routes
Method
Download

Crowd preference

#ModelRatingAgainst the leaderBoundsVotes
1Gemini 4 ArgonGoogle1,5261,519–1,53210,083
2Claude Opus 5.5Anthropic1,5161,509–1,52310,322
3Claude Fable 5.1Anthropic1,5131,507–1,51816,343
4Claude Opus 5Anthropic1,5081,504–1,51334,526
5Claude Opus 4.6Anthropic1,5011,498–1,50583,454
6Gemini 3.8 FlashGoogle1,4981,494–1,50343,997
7Claude Fable 5Anthropic1,4911,487–1,49544,253
7Muse Spark 1.3Meta1,4911,486–1,49620,506
7MiMo-V2.6-ProXiaomi1,4911,482–1,5004,067
10Claude Opus 4.7Anthropic1,4901,486–1,49365,140
Snapshot 
text arena, overall, 22 Oct 2026
Matched 
91 of 418 entries
Method
Download

Value for price

#ModelValueLower is betterBlended price / 1MRating
1Granite 4.2 3BIBM0.04$0.05251,294
2GPT OSS 20BOpenAI0.04$0.05751,287
3GPT OSS 120BOpenAI0.05$0.070251,366
4DeepSeek V4 FlashDeepSeek0.06$0.091,432
5Microsoft: Phi 4Microsoft0.07$0.08751,217
6IBM: Granite 4.2 8BIBM0.08$0.10751,319
7Qwen3 32BAlibaba0.10$0.131,340
8GPT-5 NanoOpenAI0.10$0.13751,320
9MiMo-V2.6-FlashXiaomi0.12$0.1751,452
10MiMo-V2.5Xiaomi0.12$0.1751,428
Formula 
Blended price ÷ rating × 1,000
Price 
Hopscotch published rates
Rating 
Arena Intelligence, Inc.
Covered 
91 of 91 rated models
Method
Download