Tag · 41 charts · newest first
AI Benchmarks
Our analysis and charts on AI benchmarks: coding, maths, reasoning, agents, vision and how models compare with people. Every benchmark chart, grouped by skill, is on the AI Benchmarks hub.
-
AI BenchmarksArabic.AI's LLM-X topped HELM Arabic with a mean score of 0.86, ahead of Gemini 2.5 Flash at 0.8219 Oct 2026 · Chart · CSVView →
-
AI BenchmarksGPT-5.2 leads the Indic LLM Arena with 1,314, ahead of GPT-5.1 (1,298) and Gemini 3 Flash (1,288)19 Oct 2026 · Chart · CSVView →
-
AI BenchmarksGPT-5 scored 99.8% on standard Slovenian but 88.6% on the Cerkno dialect; 8 of 12 models fell below 60%19 Oct 2026 · Chart · CSVView →
-
AI BenchmarksClaude 4.5 Opus led SWE-bench Verified at 76.8% in February 2026; the top 10 sat within 6 points19 Oct 2026 · Chart · CSVView →
-
AI BenchmarksThe best Terminal-Bench 2.0 score rose from 18.4% to 77.3% between February 2025 and February 202619 Oct 2026 · Chart · CSVView →
-
AI BenchmarksClaude Opus 4.6 led Vibe Code Bench at 57.6% in early 2026, 26 points above the lowest of eight models19 Oct 2026 · Chart · CSVView →
-
AI BenchmarksThe best model solved 31.3% of FrontierMath's hardest problems in 2025, up from 0% in 202419 Oct 2026 · Chart · CSVView →
-
AI BenchmarksGPT-5.2 (high) scored 97% on MathArena in December 2025, up from 86.4% for November's best model19 Oct 2026 · Chart · CSVView →
-
AI BenchmarksAletheia scored 91.9% on IMO-ProofBench olympiad proofs in early 2026, against 7.1% for GPT-5.119 Oct 2026 · Chart · CSVView →
-
AI BenchmarksThe top 15 models on TaxEval v2 scored within 2.9 percentage points of each other in early 202619 Oct 2026 · Chart · CSVView →
-
AI BenchmarksNo model reached 70% on MortgageTax in early 2026; Gemini 3.1 Pro Preview led at 69.4%19 Oct 2026 · Chart · CSVView →
-
AI BenchmarksKimi K2.5 led CorpFin v2's credit-agreement questions at 68.3% in early 2026; none reached 70%19 Oct 2026 · Chart · CSVView →