Skip to content
Model intelligence

678 AI models

Capability (Epoch Capabilities Index and individual benchmarks from Epoch AI), API list prices and context windows (OpenRouter), release dates and open-weight status. Benchmarks are shown individually - never merged into one invented score.
Leads on ECI
GPT-6 Astra
ECI 166.6Epoch AI
Leads on GPQA Diamond
GPT-6 Astra
95.8%Epoch AI
Leads on SWE-bench Verified
Claude Opus 4.7
83.5%Epoch AI
Cheapest in ECI top 10
GPT-5.6 Sol
$2.00/M inputOpenRouter
Longest context
Grok 4.20 Multi-Agent
2M tokensOpenRouter
Best open-weight on ECI
Kimi K3
ECI 157.68Epoch AI
Epoch Capabilities Index by release date

Capability frontier

Source: Epoch AI (CC BY 4.0). ECI is Epoch's item-response model over many benchmarks; each model page shows its 90% confidence interval.

Blended $/1M tokens (3:1 input:output) vs ECI

Price vs capability

Only models with both an ECI score and an OpenRouter price. Normalisation: 75% input + 25% output price. Click a point to open the model.

#ModelECI ↓ContextIn $/MReleased
401GPT-5.4 mini (none)———17 Mar 2026
402GPT-5.4 nano (no thinking)———17 Mar 2026
403GPT-5.4 nano (low)———17 Mar 2026
404GPT-5.4 mini (low)———17 Mar 2026
405GPT-5.4 mini (medium)———17 Mar 2026
406GPT-5.4 nano (medium)———17 Mar 2026
407GPT-5.4 nano (xhigh)———17 Mar 2026
408GPT-5.4 mini (unknown thinking)———17 Mar 2026
409GLM 5 Turbo
Z.ai (Zhipu AI)· reasoning
—203K$1.2015 Mar 2026
410Seed-2.0-Lite
ByteDance· reasoning
—262K$0.2510 Mar 2026
411GPT-5.4 Pro (web)———5 Mar 2026
412Mercury 2
Inception Labs· reasoning
—128K$0.254 Mar 2026
413Seed-2.0-Mini
ByteDance· reasoning
—262K$0.1026 Feb 2026
414Nano Banana 2 (Gemini 3.1 Flash Image Preview)
Google· reasoning
—66K$0.5026 Feb 2026
415Qwen3.5-27B
Alibaba (Qwen)· reasoning
—262K$0.2025 Feb 2026
416Qwen3.5-Flash
Alibaba (Qwen)· reasoning
—1M$0.06525 Feb 2026
417Gemini 3.1 Pro Preview Custom Tools
Google· reasoning
—1.05M$2.0025 Feb 2026
418Qwen3.5-4B———24 Feb 2026
419Qwen3.5-2B———24 Feb 2026
420Aion-2.0
AionLabs· reasoning
—131K$0.8023 Feb 2026
421Qwen3.5 Plus 2026-02-15
Alibaba (Qwen)· reasoning
—1M$0.2616 Feb 2026
422Gemini 3 Deep Think———12 Feb 2026
423Qwen3 Max Thinking
Alibaba (Qwen)· reasoning
—262K$0.789 Feb 2026
424GPT-5.3 Codex (xhigh)———5 Feb 2026
425Step 3.5 Flash
StepFun· reasoning
—262K$0.1029 Jan 2026
426Kimi K2.5 (Fireworks)———27 Jan 2026
427MiniMax M2-her—66K$0.3023 Jan 2026
428Palmyra X5—1.04M$0.6021 Jan 2026
429GPT Audio—128K$2.5019 Jan 2026
430GLM 4.7 Flash
Z.ai (Zhipu AI)· reasoning
—200K$0.06019 Jan 2026
431GPT Audio Mini—128K$0.6019 Jan 2026
432GPT-5.2-Codex
OpenAI· reasoning
—400K$1.7514 Jan 2026
433MiniMax M2.1
MiniMax· reasoning
—205K$0.3023 Dec 2025
434Seed 1.6
ByteDance· reasoning
—262K$0.2523 Dec 2025
435Seed 1.6 Flash
ByteDance· reasoning
—262K$0.07523 Dec 2025
436GLM-4.7 (Together)———22 Dec 2025
437GLM-4.7 (Novita)———22 Dec 2025
438Gemini 3 Flash Preview
Google· reasoning
—1.05M$0.5017 Dec 2025
439GPT-5.2 Pro (web)———11 Dec 2025
440GPT-5.2 Chat—128K$1.7510 Dec 2025
441GLM 4.6V
Z.ai (Zhipu AI)· reasoning
—131K$0.308 Dec 2025
442Relace Search—256K$1.008 Dec 2025
443GPT-5.1-Codex-Max
OpenAI· reasoning
—400K$1.254 Dec 2025
444Nova 2 Lite
Amazon· reasoning
—1M$0.302 Dec 2025
445Mistral Large 3———2 Dec 2025
446DeepSeek-V3.2 (Thinking; Fireworks)———1 Dec 2025
447DeepSeek-V3.2 (Thinking; Novita)———1 Dec 2025
448DeepSeek-V3.2-Speciale———1 Dec 2025
449Nano Banana Pro (Gemini 3 Pro Image Preview)
Google· reasoning
—66K$2.0020 Nov 2025
450Grok 4.1 Fast———19 Nov 2025
451Gemini 3 Pro Preview———18 Nov 2025
452Grok 4.1———17 Nov 2025
453GPT-5.1-Codex
OpenAI· reasoning
—400K$1.2513 Nov 2025
454GPT-5.1-Codex-Mini
OpenAI· reasoning
—400K$0.2513 Nov 2025
455Kimi K2 Thinking Turbo———6 Nov 2025
456Kimi K2 Thinking (Together)———6 Nov 2025
457Nova Premier 1.0—1M$2.5031 Oct 2025
458Sonar Pro Search
Perplexity· reasoning
—200K$3.0030 Oct 2025
459Voxtral Small 24B 2507—33K$0.1030 Oct 2025
460gpt-oss-safeguard-20b
OpenAI· reasoning
—131K$0.07529 Oct 2025
461granite-4.0-1b
———28 Oct 2025
462granite-4.0-350m
———28 Oct 2025
463MiniMax M2
MiniMax· reasoning
—205K$0.3023 Oct 2025
464Qwen3 VL 32B Instruct—131K$0.1023 Oct 2025
465Granite 4.0 Micro—131K$0.01720 Oct 2025
466GPT-5 Image Mini
OpenAI· reasoning
—400K$2.5016 Oct 2025
467GPT-5 Image
OpenAI· reasoning
—400K$10.014 Oct 2025
468Qwen3 VL 8B Thinking
Alibaba (Qwen)· reasoning
—131K$0.1814 Oct 2025
469Qwen3 VL 8B Instruct—262K$0.1214 Oct 2025
470Nano Banana (Gemini 2.5 Flash Image)—33K$0.307 Oct 2025
471Qwen3 VL 30B A3B Thinking
Alibaba (Qwen)· reasoning
—262K$0.206 Oct 2025
472Qwen3 VL 30B A3B Instruct—262K$0.156 Oct 2025
473tiny-recursion-model
———6 Oct 2025
474GLM 4.6
Z.ai (Zhipu AI)· reasoning
—205K$0.4330 Sep 2025
475GLM-4.6 (Together)———30 Sep 2025
476Cydonia 24B V4.1—131K$0.3027 Sep 2025
477Relace Apply 3—256K$0.8526 Sep 2025
478gemini-robotics-er-1.5-preview
———26 Sep 2025
479Gemini 2.5 Flash-Lite (Sep 2025)———25 Sep 2025
480Qwen3-Max-Instruct———24 Sep 2025
481Qwen3 Coder Plus—1M$0.6523 Sep 2025
482Qwen3 VL 235B A22B Thinking
Alibaba (Qwen)· reasoning
—131K$0.4023 Sep 2025
483Qwen3 VL 235B A22B Instruct—262K$0.2123 Sep 2025
484Qwen3 Coder Flash—1M$0.2017 Sep 2025
485GPT-5-codex———15 Sep 2025
486Qwen3 Next 80B A3B Thinking
Alibaba (Qwen)· reasoning
—262K$0.1511 Sep 2025
487Qwen3 Next 80B A3B Instruct—262K$0.1011 Sep 2025
488Qwen Plus 0728
Alibaba (Qwen)· reasoning
—1M$0.268 Sep 2025
489Kimi K2 0905 (Novita)———5 Sep 2025
490Kimi K2 Instruct (0905)———5 Sep 2025
491Kimi K2 (Sep 2025)———5 Sep 2025
492Kimi K2 0905—262K$0.604 Sep 2025
493grok-code-fast-1———28 Aug 2025
494Hermes 4 405B
Nous Research· reasoning
—131K$1.0026 Aug 2025
495seed-oss-36b-instruct
———20 Aug 2025
496nvidia-nemotron-nano-9b-v2
———18 Aug 2025
497GLM 4.5V
Z.ai (Zhipu AI)· reasoning
—66K$0.6011 Aug 2025
498GPT-5 mini (minimal)———7 Aug 2025
499GPT-5 nano (low)———7 Aug 2025
500GPT-5 nano (minimal)———7 Aug 2025
Showing 100 of 678. Benchmark cells are % (best reported setting). 3.8K benchmark results in total.← PrevNext →Export CSV