Cloud BenchmarksLocal Benchmarks

☁️ Cloud Benchmarks ☁️

I run cron jobs to periodically test the token generation speed of different cloud LLM providers. The chart helps visualize the distributions of different speeds, as they can vary somewhat depending on the loads. For readability not all models are shown, but you can see the full results in the table below.

Every provider and model now has a dedicated landing page with narrative insights, SEO-friendly metadata, and structured data for search engines. Click any provider or model in the table to explore performance in depth.

I am working daily to add more providers and models, looking anywhere that does not require purchasing dedicated endpoints for hosting (why some models may appear to be missing). If you have any more suggestions let me know on GitHub!! 😊

Fastest Models Right Now (updated <24h)

#ModelProviderSpeed
1llama-3.1-8bgroq281 tok/s
2qwen-3-32bcerebras253 tok/s
3qwen-3-32bgroq240 tok/s
4llama-3.1-8bcerebras225 tok/s
5llama-3.3-70bcerebras215 tok/s

📊 Speed Distribution 📊

📚 Full Results 📚

Showing 86 of 86 modelsFlagged statuses: likely_deprecated, deprecated, failing, stale, never_succeeded, disabled
Status
groqllama-3.1-8bActive3h ago281.0095447130.00
cerebrasqwen-3-32bActive3h ago253.004417370.00
groqqwen-3-32bActive3h ago240.0046391150.00
cerebrasllama-3.1-8bActive3h ago225.006365530.00
cerebrasllama-3.3-70bActive3h ago215.0014338370.00
cerebrasgpt-oss-120bActive3h ago212.004346750.00
groqllama-3.3-70bActive3h ago206.0079280120.00
groqllama-4-scoutActive3h ago195.0023316250.00
groqllama-4-maverickActive3h ago165.0019310510.00
cerebrasqwen-3-235b-instructActive4d ago164.002264790.00
togetherllama-3.1-8bActive6h ago155.002230580.00
groqkimi-k2Active3h ago140.0021203250.00
bedrocknova-microActive21m ago128.0069154260.00
togethermistral-7bActive3h ago109.003166410.00
bedrockllama-4-maverickActive21m ago109.0028149250.00
openaio3 MiniNever Succeeded(Medium)3h ago104.00201510.00
bedrocknova-liteActive21m ago102.0042135290.00
bedrockllama-4-scoutActive21m ago102.001140340.00
bedrockllama-3.3-70bActive21m ago101.0015137230.00
togetherqwen-2.5-7bActive3h ago100.003146270.00
bedrocknova-proActive21m ago82.5010124410.00
openaigpt-3.5-turboActive3h ago77.4012129460.00
openaigpt-4.1-nanoActive3h ago77.2013138400.00
googleActive3h ago73.7034105590.00
togetherllama-3.2-3bActive3h ago72.9051451160.00
togetherllama-3.1-70bActive3h ago72.704147490.00
googleclaude-3-haikuActive20d ago67.602779530.00
openaigpt-4oActive3h ago64.0071411410.00
fireworksmixtral-8x22bActive3h ago61.503783570.00
googlegemini-2.0-flashActive4d ago61.40888590.00
googlegemini-2.0-flash-liteActive4d ago61.101181610.00
googlegemini-2.5-flashNever Succeeded(Medium)3h ago61.107781190.00
togetherllama-3.3-70bActive3h ago51.9021361480.00
anthropicclaude-haiku-4.5Active3h ago51.401580620.00
togetherqwen-2.5-72bActive1d ago50.90371490.00
deepinframixtral-8x22bStale(Medium)3h ago50.002680300.00
openaio4 MiniNever Succeeded(Medium)3h ago49.5015750.00
togethermixtral-8x7bActive3h ago49.106111330.00
bedrockllama-3.2-90bActive21m ago47.402951340.00
openaigpt-4.1-miniActive3h ago47.001897480.00
deepinfrallama-3-8bStale(Medium)3h ago45.60771300.00
bedrockclaude-haiku-4.5Active22m ago45.40865890.00
deepinframistral-7bStale(Medium)3h ago45.10389540.00
bedrockmistral-largeActive21m ago44.00847240.00
fireworksllama-3.3-70bActive3h ago41.906781250.00
deepinfradevstral-smallNever Succeeded(Medium)3h ago41.80384500.00
googlegemini-2.5-proNever Succeeded(Medium)3h ago41.0015631590.00
openaigpt-4o-miniActive3h ago39.60886420.00
openaiGPT-5.1-codex-maxActive3h ago38.9011041500.00
deepinfrallama-3.2-90bStale(Medium)3h ago38.50193860.00
togetherdeepseek-r1Active3h ago38.001681770.00
deepinfrallama-3.1-8bStale(Medium)3h ago37.3011021250.00
googleclaude-3-5-sonnetActive20d ago34.702446720.00
openaigpt-4.1Active3h ago34.50767450.00
openaigpt-4-turboActive3h ago33.90251560.00
deepinfrallama-2-70bStale(Medium)3h ago33.20844380.00
bedrockclaude-3-7-sonnetActive22m ago32.90142790.00
deepinfrallama-3-70bStale(Medium)3h ago32.80244520.00
bedrockclaude-3-5-sonnetActive22m ago32.60742570.00
deepinfraqwen-2.5-72bStale(Medium)3h ago31.90247870.00
deepinfraQwen 2.5 Coder 32BNever Succeeded(Medium)3h ago31.801674650.00
togetherdeepseek-v3Active15d ago29.001671390.00
bedrockclaude-3-5-haikuActive22m ago29.001381250.00
openaiGPT-5.1Active3h ago28.003561090.00
openaiGPT-5.2Active3h ago27.60944990.00
deepinfrallama-3.2-3bStale(Medium)3h ago27.10190640.00
deepinfrallama-3.2-1bStale(Medium)3h ago26.60483370.00
openaigpt-4Active3h ago26.10252610.00
openaiGPT-5.1-codexActive3h ago25.90449880.00
deepinfrallama-3.3-70bNever Succeeded(Medium)3h ago23.50159820.00
deepinfraqwen-3-235bNever Succeeded(Medium)3h ago22.00143530.00
bedrockclaude-sonnet-4.5Active22m ago21.601291800.00
togetherllama-3.1-405bActive2d ago21.401301420.00
deepinfrallama-3.1-70bStale(Medium)3h ago21.20339530.00
openaiGPT-5.1-codex-miniActive3h ago21.001451030.00
anthropicclaude-4-sonnetActive3h ago20.408321570.00
anthropicclaude-opus-4.5Active3h ago19.7011301710.00
anthropicClaude Opus 4.1Active3h ago19.005251320.00
bedrockclaude-3-opusActive22m ago19.00422850.00
anthropicclaude-4-opusActive3h ago18.104241190.00
bedrockclaude-opus-4.5Active22m ago18.001232240.00
deepinfrallama-3.1-405bStale(Medium)3h ago17.201313040.00
deepinfrallama-3.2-11bStale(Medium)3h ago14.001682020.00
openaiActive3h ago11.706182130.00
openaio1-proLikely Deprecated(Medium)3h ago9.86119100.00
openaiGPT-5.2-proActive3h ago4.241125710.00
Lifecycle snapshot
Loading status summary…

📈 Time Series 📈

llama-3.3-70b

llama-3.1-8b

claude-3-5-sonnet

claude-haiku-4.5

claude-opus-4.5

llama-3.1-405b

llama-3.1-70b

llama-3.2-3b

llama-3.2-90b

llama-4-maverick

llama-4-scout

mistral-7b

mixtral-8x22b

qwen-2.5-72b

qwen-3-32b

undefined

Claude Opus 4.1

claude-3-5-haiku

claude-3-7-sonnet

claude-3-opus

claude-4-opus

claude-4-sonnet

claude-sonnet-4.5

deepseek-r1

devstral-small

gemini-2.0-flash

gemini-2.0-flash-lite

gemini-2.5-flash

gemini-2.5-pro

gpt-3.5-turbo

gpt-4

gpt-4-turbo

gpt-4.1

gpt-4.1-mini

gpt-4.1-nano

gpt-4o

gpt-4o-mini

GPT-5.1

GPT-5.1-codex

GPT-5.1-codex-max

GPT-5.1-codex-mini

GPT-5.2

GPT-5.2-pro

gpt-oss-120b

kimi-k2

llama-2-70b

llama-3-70b

llama-3-8b

llama-3.2-11b

llama-3.2-1b

mistral-large

mixtral-8x7b

nova-lite

nova-micro

nova-pro

o1-pro

o3 Mini

o4 Mini

Qwen 2.5 Coder 32B

qwen-2.5-7b

qwen-3-235b

qwen-3-235b-instruct