Beta

AI Models with 1M+ Context

AI models with 1 million+ token context windows ranked by score. Compare Gemini, Claude, and other long-context models.

25
Models
8
Providers
2
Open Source
$1.25
Median $/1M in
#ModelAvgaider editaider poly?ANLI?APEX-Agents?ARC AI2?ARC-AGI?ARC-AGI-2?aa agenticaa coding aa qualityseal audioseal audioseal audioBalrog?BBH?hf bbhC-EvalCadEval?charxiv recharxiv rearena elo arena elo chess puzz?CMMLUCSQA2Cybench?deepresear?EnigmaEvalfiction li?Fortressfrontierma?frontierma?GeoBench?GPQAGPQA diamond?graphwalksGSM8K?GSO-Bench?HellaSwag?HELM · GPQAhelm ifevahelm mmlu helm omni helm wildbHLE?hle toolsseal humanseal humanIFEvaljp jcommonJHumanEvalJMMLUJNLIJSQuADLAMBADA?lech mazur?livebench livebench livebench livebench livebench livebench livebench livebench jp overallMASKMATH level 5?MATH Level 5MCP AtlasMMLU?MMLU-PROMMMLUmmmlu armmmlu bnmmmlu zhmmmlu frmmmlu demmmlu himmmlu idmmmlu itmmmlu jammmlu kommmlu ptmmmlu esmmmlu swmmmlu yoseal multiMultiNRCMUSROpenBookQA?oc aime202oc gpqa dioc hleoc ifevaloc livecodoc mmlu prOSWorld?otis mock ?PIQA?posttrainbseal pro rseal pro rseal propeseal remotScienceQA?SciPredictSimpleBench?simpleqa v?seal swe aseal swe aswe bench swe bench swe bench seal swe bseal swe bswe bench swe bench ?terminal b?the agent ?TriviaQA?TutorBenchUSAMOVideoMME?VISTAseal visuaVPCT?WeirdML?Winogrande?$/1M inContextReleased
1Anthropic logoClaude Mythos Preview🇺🇸 Anthropic100.0------------------86.193.2--------------94.580.0--------56.864.7-------------------------92.7------------------------79.6-------------87.359.077.8--93.9-82.0---97.6------N/A1.0MApr 269d ago
2OpenAI logoGPT-5.4 Pro🇺🇸 OpenAI93.0-----94.583.3---------------58.6-------50.037.5--92.8-----------------------------------------------------------------------68.947.8--------------------$30.001.1MMar 261mo ago
3Google DeepMind logoGemini 3.1 Pro Preview🇺🇸 Google DeepMind90.0---33.5-98.077.159.155.557.2----------1455.71492.655.0----19.8--36.916.7--92.1---------------------------------------------------71.464.7---------95.6-21.6------75.577.3-------75.6-78.4------29.0-72.1-$2.001.0MFeb 261mo ago
4Alibaba Qwen logoQwen3.6 Plus🇨🇳 Alibaba QwenOpen88.7-------61.742.950.0----------------------------------------------55.078.269.958.375.083.770.875.8----------------------------------------------------------------$0.331.0MApr 2614d ago
5OpenAI logoGPT-5.4🇺🇸 OpenAI83.4---35.9-93.774.069.457.357.2-----------1465.844.0-------47.627.1--91.1--------------------------------------------------------------95.3-20.2-------44.8-------76.9----------57.4-$2.501.1MMar 261mo ago
6Anthropic logoClaude Opus 4.6 (Fast)🇺🇸 Anthropic83.3-------67.648.153.0----------1546.21502.8-------------------------------------------96.3----------------------------------53.352.3-4.2----33.336.7--------------27.5---$30.001.0MApr 269d ago
7Anthropic logoClaude Opus 4.6🇺🇸 Anthropic81.1---31.7-94.069.2-------------1542.91496.617.0--93.0----40.722.9--87.4--33.3------31.1----------------------------------------------------94.4-23.2------61.146.5-------78.7-74.7--------77.9-$5.001.0MFeb 262mo ago
8Google DeepMind logoGemini 2.5 Pro Preview 06-05🇺🇸 Google DeepMind73.5-83.1---------------------------------------------------------------------------------------------------------------10.1------55.6--54.6----$1.251.0MJun 2510mo ago
9Google DeepMind logoGemini 2.5 Pro🇺🇸 Google DeepMind67.2-83.1---41.04.932.731.934.646.9-46.943.3---64.0--1202.01448.220.0---49.7-91.7-14.14.281.0-80.4--3.9-74.984.086.341.685.717.7----------86.0----------95.6-----------------------88.784.721.190.071.385.8-84.7--------54.956.0-------57.6-32.630.3------19.654.0-$1.251.0MJun 2510mo ago
10xiaomi logoMiMo-V2-Pro🇨🇳 xiaomi62.9-------62.841.449.2----------1433.41445.0----------------------------------30.068.849.243.269.177.058.169.7----------------------------------------------------------------$1.001.0MMar 2629d ago
11Google DeepMind logoGemini 3 Flash Preview🇺🇸 Google DeepMind59.2---24.0-21.533.649.742.646.4---48.1------1436.41473.938.0-------35.64.288.0-77.6--9.8------------------------------57.4----------------------------92.8-------22.253.367.4-------75.4-64.3-------58.961.6-$0.501.0MDec 254mo ago
12writer logoPalmyra X5🇺🇸 writer57.0---------------------------------------66.182.380.441.578.0------------------------------------------------------------------------------------$0.601.0MJan 262mo ago
13Anthropic logoClaude Sonnet 4.6🇺🇸 Anthropic52.6-----86.560.463.050.951.7----------1521.01462.213.0-------32.48.3--83.2--------------------------------------------------------------85.8-16.4-------29.031.231.8-----75.2----------66.1-$3.001.0MFeb 261mo ago
14xAI logoGrok 4 Fast🇺🇸 xAI51.6-----48.55.3------------------30.0--94.4--------------------------81.1----------------------------------------------------------------------42.9-$0.202.0MSep 256mo ago
15Anthropic logoClaude Sonnet 4.5🇺🇸 Anthropic50.8-----63.713.6---------------12.0--60.052.6---15.24.2--76.4--14.7------9.4---------------------97.7-----------------------------62.977.8-9.9------45.223.6-------71.370.646.5-------9.747.7-$3.001.0MSep 256mo ago
16Google DeepMind logoGemini 2.0 Flash Lite🇺🇸 Google DeepMind45.3---------------------------------------50.082.472.037.479.0------------------------------------------------------------------------------------$0.071.0MFeb 251y ago
17Google DeepMind logoGemini 2.0 Flash🇺🇸 Google DeepMind44.7-38.2----1.3----------30.0---1360.0------61.1-1.7-77.0-52.2----55.684.173.745.980.0-----------71.5----------82.2--72.9---------------------------31.0--------17.3-----------11.4-------25.8-$0.101.0MFeb 251y ago
18Anthropic logoClaude Sonnet 4🇺🇸 Anthropic43.7-61.3---40.05.9------------------35.047.8-46.9-4.10.137.0-72.3--4.9------3.1--------------------95.384.4-----------------------68.774.68.788.347.583.043.971.1--------34.6---------64.9-33.1------1.046.1-$3.001.0MMay 2510mo ago
19OpenAI logoGPT-4.1 Mini🇺🇸 OpenAI43.1-32.4---3.50.1----------16.0----------44.4-4.5---54.5----61.490.478.349.183.8----------------------87.3------------------------------44.7------------------23.9---------37.6-$0.401.0MApr 251y ago
20OpenAI logoGPT-4.1🇺🇸 OpenAI41.2-52.4---5.50.4----------42.0--------29.3-63.9-5.50.172.0-55.9----65.983.881.147.185.40.6---------------------83.0------------------------------38.3--------12.4--------48.539.6---------39.0-$2.001.0MApr 251y ago
21Google DeepMind logoGemini 2.5 Flash🇺🇸 Google DeepMind38.1-47.1---32.32.5---40.0-40.033.5-------1411.0----29.2-47.2-4.84.273.0------39.089.863.938.481.77.7----------76.5-----------------------------------------73.0--------29.4----------17.141.1------7.041.0-$0.301.0MJun 2510mo ago
22Google DeepMind logoGemini 2.5 Flash Lite🇺🇸 Google DeepMind33.2-------11.718.121.6-----------------------------30.981.053.748.081.8------------------------------------------------------------------------------------$0.101.0MJul 258mo ago
23OpenAI logoGPT-4.1 Nano🇺🇸 OpenAI25.8-8.9---0.10.1---------------------25.0-1.0---31.9----50.784.355.036.781.1----------------------70.0------------------------------28.8----------------------------19.0-$0.101.0MApr 251y ago
24Meta logoLlama 4 Maverick🇺🇸 MetaOpen22.0-15.6---4.40.17.215.618.4------------------46.2-0.7-52.0-56.0---------0.9----------63.7----------73.0------------------------------20.5--------13.2---------21.0---------24.5-$0.151.0MApr 251y ago
90+ Gold 80-89 70-79 60-69 <60Scores in % unless noted. Avg = unweighted mean across tested benchmarks.

All AI models with context windows of 1 million tokens or more, ranked by benchmark score. Long-context models can process entire codebases, books, or document collections in a single prompt.

Which AI models have the largest context window?

Several models now support 1M+ token contexts, including models from Google (Gemini), Anthropic (Claude), and others. The leaderboard above lists them all.

Does context window size affect quality?

Most models maintain strong performance within their stated context window, though some show degradation at the extremes. Benchmark scores above reflect overall model quality, not context-specific performance.