AI Benchmark Digest — 2026-06-24

View on AI Benchmark Hub

Daily

New Benchmarks (7)

• You're Absolutely Right! (Average anti-sycophancy score (1-5)): Claude Opus 4.8 leads with 4.5 across 16 models. Typebulb sycophancy benchmark with eight single- and multi-turn pressure prompts, scored 1-5 by a Gemini judge where higher scores mean the model resisted user-pleasing agreement and stayed truth-following.
• OpenAI ChatGPT Pro - AIME 2024 (pass@1 accuracy (%)): O1 Pro leads with 86.0 across 3 models. OpenAI ChatGPT Pro launch result for AIME 2024 pass@1 accuracy, comparing o1-preview, o1, and o1 pro mode.
• OpenAI ChatGPT Pro - Codeforces (pass@1 percentile): O1 Pro leads with 90.0 across 3 models. OpenAI ChatGPT Pro launch result for Codeforces pass@1 percentile, comparing competitive-programming performance across o1 variants.
• OpenAI ChatGPT Pro - GPQA Diamond (pass@1 accuracy (%)): O1 Pro leads with 79.0 across 3 models. OpenAI ChatGPT Pro launch result for GPQA Diamond pass@1 accuracy, testing graduate-level science reasoning across o1 variants.
• OpenAI ChatGPT Pro - AIME 2024 4/4 Reliability (4/4 reliability (%)): O1 Pro leads with 80.0 across 3 models. OpenAI ChatGPT Pro launch result for AIME 2024 4/4 reliability, where a question counts only if all four model attempts are correct.
• OpenAI ChatGPT Pro - Codeforces 4/4 Reliability (4/4 reliability percentile): O1 Pro leads with 75.0 across 3 models. OpenAI ChatGPT Pro launch result for Codeforces 4/4 reliability percentile, using the worst-performing solution across four model samples.
• OpenAI ChatGPT Pro - GPQA Diamond 4/4 Reliability (4/4 reliability (%)): O1 Pro leads with 74.0 across 3 models. OpenAI ChatGPT Pro launch result for GPQA Diamond 4/4 reliability, where an item counts only if all four attempts are correct.

New Scores From Top-10 Models (1)

• GPT-5.5 on CADGenBench: 0.4111 Aggregate CAD Score (#3/14)

New #1 Leaders (1)

• AA Omniscience - Health (Accuracy (%)): Grok Build 0.1 0616 (48.9) beat GPT-5.5 (Medium) (48.8) by 0.1.