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?

RankModelMulti idxAI2DMMMU-ProChartQADocVQAMathVistaMMMUReleasedCountryTypeAccessParamsCutoffContextSpeedLatencyIn $/MOut $/M
#1OpenAI82.984.381.62025multimodalAPI only2024200K1155.20$1.10$4.40
Index 53.1 = (55.0 + 48.1 + 49.7 + 59.6 / 4) — equal-weighted mean of 4 components.
General25%
55
  • SimpleQA
  • AA-LCR55
  • LongBench-v2
  • IFBench
Reasoning25%
48.1
  • GPQA Diamond81.4
  • Humanity’s Last Exam14.7
  • FrontierMath
  • ARC-AGI-2
Coding25%
49.7
  • SWE-bench Verified68.1
  • Terminal-Bench15.2
  • Aider Polyglot68.9
  • SciCode46.5
Tool use & agents25%
59.6
  • TAU-bench Retail71.8
  • τ²-bench55.6
  • BFCL
  • BrowseComp51.5
#2OpenAI8276.486.882.92025llmAPI only2024200K5020.00$2.00$8.00
Index 56.3 = (69.3 + 33.6 + 57.1 + 65.2 / 4) — equal-weighted mean of 4 components.
General25%
69.3
  • SimpleQA
  • AA-LCR69.3
  • LongBench-v2
  • IFBench
Reasoning25%
33.6
  • GPQA Diamond87.7
  • Humanity’s Last Exam24.3
  • FrontierMath15.8
  • ARC-AGI-26.5
Coding25%
57.1
  • SWE-bench Verified69.1
  • Terminal-Bench37.1
  • Aider Polyglot81.3
  • SciCode41
Tool use & agents25%
65.2
  • TAU-bench Retail
  • τ²-bench80.7
  • BFCL
  • BrowseComp49.7
#3Mistral AI81.793.888.193.369.4642024multimodalAPI only2024131K00.50$2.00$6.00
Index 25.8 = (10.3 + 27.1 + 29.2 + 36.5 / 4) — equal-weighted mean of 4 components.
General25%
10.3
  • SimpleQA
  • AA-LCR10.3
  • LongBench-v2
  • IFBench
Reasoning25%
27.1
  • GPQA Diamond50.5
  • Humanity’s Last Exam3.6
  • FrontierMath
  • ARC-AGI-2
Coding25%
29.2
  • SWE-bench Verified
  • Terminal-Bench
  • Aider Polyglot
  • SciCode29.2
Tool use & agents25%
36.5
  • TAU-bench Retail
  • τ²-bench36.5
  • BFCL
  • BrowseComp
Amazon81.589.293.561.72024multimodalAPI only300K1000.50$0.80$3.20
OpenAI81.378.484.22025llmAPI only2024400K1002.00$1.25$10.00
Meta80.888.894.470.769.42025multimodalOpen weights109B total / 17B active (MoE)202410M7760.31$0.08$0.30
Google79.779.72025multimodalAPI only20251M850.70$0.30$2.50
Google79.679.62025multimodalAPI only20251M850.70$1.25$10.00
Amazon78.586.892.456.22024multimodalAPI only300K1000.50$0.06$0.24
Meta78.259.69094.473.773.42025multimodalOpen weights400B total / 17B active (MoE)20241M6390.20$0.15$0.60
xAI78782025multimodalAPI only2024128K1000.70$3.00$15.00
OpenAI77.794.259.985.792.861.472.22024multimodalAPI only2023128K1320.50$2.50$10.00
Anthropic77.377.32026llmAPI only1M481.65$5.00$25.00
Anthropic75752025llmAPI only200K1010.40$3.00$15.00
OpenAI74.771.877.62024llmAPI only2023200K660.54$15.00$60.00
Anthropic74.474.42025llmAPI only20251M1010.40$3.00$15.00
OpenAI73.872.375.22025multimodalAPI only128K5020.00$75.00$150.00
OpenAI73.572.274.82025multimodalAPI only20241M10010.00$2.00$8.00
OpenAI72.973.172.72025multimodalAPI only20241M1505.00$0.40$1.60
Google72.972.92025multimodalAPI only20251M60.44$0.10$0.40
Google70.770.72024multimodalAPI only20241M1830.40$0.10$0.40
Meta66.491.13383.488.451.550.72024multimodalOpen weights106000000002023128K1680.20$0.05$0.05
OpenAI55.856.255.42025multimodalAPI only20241M2002.00$0.10$0.40

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