AI War Tracker
298 models in catalog

AI models

Every model we track — frontier flagships, open-weights specialists, narrow benchmarks-only releases. Filter by lab, country, access, modality, or release window. Sorted by newest by default; head to the leaderboard for the ranked view.

Leaderboard →Labs →Benchmarks →

Updated May 29, 2026 · Benchmarks via Artificial Analysis, specs & pricing via OpenRouter · Methodology · Spotted an error?

RankModelReason idxBIG-Bench HardARC-AGI-2DROPGPQA DiamondReleasedCountryTypeAccessParamsCutoffContextSpeedLatencyIn $/MOut $/M
#1Anthropic94.294.22026llmAPI only1M491.42$5.00$25.00
#2OpenAI93.593.52026llmAPI only20251.1M670.97$5.00$30.00
#3Alibaba92.392.32026llmAPI only1M2031.59$1.25$3.75
#4Google92.292.22026multimodalAPI only20251M2219.75$1.50$9.00
#5Anthropic92922026llmAPI only1M666.54$5.00$25.00
#6OpenAI92922026llmAPI only1.1M840.63$2.50$15.00
#7OpenAI91.591.52026multimodalAPI only400K7381.08$1.75$14.00
#8Moonshot AI91.191.12026llmOpen weights1T (32B active)262K571.20$0.73$3.49
#9xAI91.191.12026llm1050.70$2.00$6.00
#10Google90.490.42025multimodalAPI only1M1911.05$0.50$3.00
#11DeepSeek90.190.12026llmOpen weights1.6T (49B active)1M301.16$0.44$0.87
#12xAI90.190.12026llmAPI only1M880.52$1.25$2.50
#13OpenAI89.989.92026multimodalAPI only400K1062.08$1.75$14.00
#14DeepSeek89.489.42026llmOpen weights284B (13B active)1M1090.76$0.10$0.20
#15Alibaba89.389.32026multimodalOpen weights262K531.82$0.39$2.34
#16Alibaba88.888.82026llmAPI only262K362.79$1.04$6.24
#17xAI88.588.52026llm970.62$2.00$6.00
#18Meta88.488.42026multimodalAPI only$0.00$0.00
#19Alibaba88.288.22026multimodalAPI only1M521.73$0.33$1.95
#20OpenAI88.188.12025llmAPI only400K1150.77$1.25$10.00
#21Moonshot AI87.987.92026multimodalOpen weights1T (32B active)262K351.33$0.40$1.90
#22OpenAI87.587.52026llmAPI only2025400K1620.63$0.75$4.50
#23MiniMax87.487.42026llmOpen weights205K501.32$0.28$1.20
#24OpenAI87.387.32025llmAPI only2024400K1002.00$1.25$10.00
#25DeepSeek87.187.12025llmOpen weights164K$0.29$0.43

Ranked on Reasoning. Cell colors show relative standing within each column (red → yellow → green). Scores are curated approximations — see each model for sources.