Event engine

AI news & updates

1,116 normalised events from official feeds, the technology press, model listings, benchmark releases and change detection. 4 events group multiple articles; the strongest source (official first, then earliest) is shown as primary. Article text is never copied - only titles, publisher summaries and links.

803 events

2 filters:

803 events

JSON

Benchmark32d ago
Epoch AI evaluates GPT-5.6 Luna (low)
FrontierMath-Tiers-1-3-v2-Private 41.4%
Epoch AI Benchmarking HubGPT-5.6 Luna (low)OpenAI
Benchmark32d ago
Epoch AI evaluates Qwen 3.6 Flash (2026-04-16)
FrontierMath-Tiers-1-3-v2-Private 17.2% · FrontierMath-Tiers-1-3-v2-Private 22.5%
Epoch AI Benchmarking HubQwen 3.6 Flash (2026-04-16)Alibaba (Qwen)
Benchmark32d ago
Epoch AI evaluates Qwen 3.6 Plus (2026-04-02)
FrontierMath-Tiers-1-3-v2-Private 32.3%
Epoch AI Benchmarking HubQwen 3.6 Plus (2026-04-02)Alibaba (Qwen)
Benchmark32d ago
Epoch AI evaluates Qwen3.6 35B A3B
FrontierMath-Tiers-1-3-v2-Private 17.5%
Epoch AI Benchmarking HubQwen3.6 35B A3B Alibaba (Qwen)
Benchmark32d ago
Epoch AI evaluates Qwen3.6 27B
FrontierMath-Tiers-1-3-v2-Private 34.0%
Epoch AI Benchmarking HubQwen3.6 27B Alibaba (Qwen)
Benchmark32d ago
Epoch AI evaluates GLM 5.1
FrontierMath-Tiers-1-3-v2-Private 36.8%
Epoch AI Benchmarking HubGLM 5.1 Z.ai (Zhipu AI)
Benchmark32d ago
Epoch AI evaluates Kimi K3 (low)
Mystery Game Puzzles 12.0%
Epoch AI Benchmarking HubKimi K3 (low)Moonshot AI
Benchmark32d ago
Epoch AI evaluates Kimi K2.6
Mystery Game Puzzles 12.0%
Epoch AI Benchmarking HubKimi K2.6 Moonshot AI
Open release33d ago
Tencent releases Hy4 preview
Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that...
OpenRouter models APIHy4 preview Tencent
Open release33d ago
Tencent releases Tencent Hy4 preview (unknown)
Epoch AI Benchmarking HubTencent Hy4 preview (unknown)Tencent
Benchmark33d ago
Epoch AI evaluates granite-4.0-1b
GPQA diamond 24.0%
Epoch AI Benchmarking Hubgranite-4.0-1b
Benchmark33d ago
Epoch AI evaluates Qwen3.5-35B-A3B
GPQA diamond 81.2% · GPQA diamond 83.5% · Chess Puzzles 1.0%
Epoch AI Benchmarking HubQwen3.5-35B-A3B Alibaba (Qwen)
Benchmark33d ago
Epoch AI evaluates qwen3-4b-instruct-2507
GPQA diamond 45.8% · OTIS Mock AIME 2024-2025 52.2% · Chess Puzzles 4.0%
Epoch AI Benchmarking Hubqwen3-4b-instruct-2507
Benchmark33d ago
Epoch AI evaluates Qwen3-4B
GPQA diamond 43.6% · GPQA diamond 52.3% · Chess Puzzles 1.0%
Epoch AI Benchmarking HubQwen3-4B Alibaba (Qwen)
Benchmark33d ago
Epoch AI evaluates Qwen3 32B
GPQA diamond 65.7% · Chess Puzzles 1.0% · Chess Puzzles 5.0%
Epoch AI Benchmarking HubQwen3 32B Alibaba (Qwen)
Benchmark33d ago
Epoch AI evaluates Qwen3 14B
GPQA diamond 53.4% · GPQA diamond 63.8% · OTIS Mock AIME 2024-2025 66.4%
Epoch AI Benchmarking HubQwen3 14B Alibaba (Qwen)
Benchmark33d ago
Epoch AI evaluates Qwen3-1.7B
GPQA diamond 30.6% · GPQA diamond 38.0% · OTIS Mock AIME 2024-2025 8.1% · Chess Puzzles 0.0%
Epoch AI Benchmarking HubQwen3-1.7B Alibaba (Qwen)
Benchmark33d ago
Epoch AI evaluates Mistral Small 3.2
GPQA diamond 49.1%
Epoch AI Benchmarking HubMistral Small 3.2 Mistral AI
Benchmark33d ago
Epoch AI evaluates granite-4.0-350m
GPQA diamond 11.2% · OTIS Mock AIME 2024-2025 0.3% · Chess Puzzles 0.0%
Epoch AI Benchmarking Hubgranite-4.0-350m
Benchmark33d ago
Epoch AI evaluates Gemma 3 4B
GPQA diamond 23.2% · OTIS Mock AIME 2024-2025 7.5% · Chess Puzzles 0.0%
Epoch AI Benchmarking HubGemma 3 4B Google
Benchmark33d ago
Epoch AI evaluates Gemma 3 1B
GPQA diamond 19.9% · OTIS Mock AIME 2024-2025 1.1% · Chess Puzzles 0.0%
Epoch AI Benchmarking HubGemma 3 1B Google
Benchmark33d ago
Epoch AI evaluates Gemma 3 12B
GPQA diamond 39.5% · OTIS Mock AIME 2024-2025 16.7% · Chess Puzzles 0.0%
Epoch AI Benchmarking HubGemma 3 12B Google
Benchmark33d ago
Epoch AI evaluates DeepSeek-R1-Distill-Qwen-32B
GPQA diamond 64.1% · OTIS Mock AIME 2024-2025 55.6% · Chess Puzzles 1.0%
Epoch AI Benchmarking HubDeepSeek-R1-Distill-Qwen-32B DeepSeek
Benchmark33d ago
Epoch AI evaluates DeepSeek-R1-Distill-Qwen-1.5B
GPQA diamond 33.6% · OTIS Mock AIME 2024-2025 21.4% · Chess Puzzles 0.0%
Epoch AI Benchmarking HubDeepSeek-R1-Distill-Qwen-1.5B DeepSeek
Benchmark33d ago
Epoch AI evaluates deepseek-r1-0528-qwen3-8b
GPQA diamond 9.3% · OTIS Mock AIME 2024-2025 43.9% · Chess Puzzles 3.0%
Epoch AI Benchmarking Hubdeepseek-r1-0528-qwen3-8b
Benchmark33d ago
Epoch AI evaluates QwQ-32B
GPQA diamond 65.3% · OTIS Mock AIME 2024-2025 59.2% · Chess Puzzles 5.0%
Epoch AI Benchmarking HubQwQ-32B Alibaba (Qwen)
Benchmark33d ago
Epoch AI evaluates Gemini 3.1 Flash Lite
FrontierMath-Tiers-1-3-v2-Private 21.4%
Epoch AI Benchmarking HubGemini 3.1 Flash Lite Google
Benchmark33d ago
Epoch AI evaluates Qwen3.6 27B
FrontierMath-Tiers-1-3-v2-Private 35.1%
Epoch AI Benchmarking HubQwen3.6 27B Alibaba (Qwen)
Benchmark33d ago
Epoch AI evaluates GLM 5.1
FrontierMath-Tiers-1-3-v2-Private 24.9%
Epoch AI Benchmarking HubGLM 5.1 Z.ai (Zhipu AI)
Benchmark33d ago
Epoch AI evaluates GPT-5.4 nano (no thinking)
FrontierMath-Tiers-1-3-v2-Private 4.6%
Epoch AI Benchmarking HubGPT-5.4 nano (no thinking)OpenAI
Benchmark33d ago
Epoch AI evaluates GPT-5.4 mini (none)
FrontierMath-Tiers-1-3-v2-Private 17.2%
Epoch AI Benchmarking HubGPT-5.4 mini (none)OpenAI
Benchmark33d ago
Epoch AI evaluates GPT-5.4 nano (low)
FrontierMath-Tiers-1-3-v2-Private 20.4%
Epoch AI Benchmarking HubGPT-5.4 nano (low)OpenAI
Benchmark33d ago
Epoch AI evaluates GPT-5.4 mini (low)
FrontierMath-Tiers-1-3-v2-Private 24.6%
Epoch AI Benchmarking HubGPT-5.4 mini (low)OpenAI
Benchmark33d ago
Epoch AI evaluates Qwen3.5-Flash
FrontierMath-Tiers-1-3-v2-Private 18.2% · FrontierMath-Tiers-1-3-v2-Private 9.5%
Epoch AI Benchmarking HubQwen3.5-Flash Alibaba (Qwen)
Benchmark33d ago
Epoch AI evaluates Qwen3.5 397B A17B
FrontierMath-Tiers-1-3-v2-Private 29.5%
Epoch AI Benchmarking HubQwen3.5 397B A17B Alibaba (Qwen)
Benchmark33d ago
Epoch AI evaluates o1
FrontierMath-Tiers-1-3-v2-Private 14.7%
Epoch AI Benchmarking Hubo1 OpenAI
Benchmark33d ago
Epoch AI evaluates DeepSeek LLM 67B
OTIS Mock AIME 2024-2025 0.8% · Chess Puzzles 0.0%
Epoch AI Benchmarking HubDeepSeek LLM 67B DeepSeek
Benchmark33d ago
Epoch AI evaluates seed-oss-36b-instruct
OTIS Mock AIME 2024-2025 67.5% · Chess Puzzles 13.0%
Epoch AI Benchmarking Hubseed-oss-36b-instruct
Benchmark33d ago
Epoch AI evaluates Qwen3.5-4B
OTIS Mock AIME 2024-2025 55.8%
Epoch AI Benchmarking HubQwen3.5-4B Alibaba (Qwen)
Benchmark33d ago
Epoch AI evaluates Qwen3 30B A3B
OTIS Mock AIME 2024-2025 62.8%
Epoch AI Benchmarking HubQwen3 30B A3B Alibaba (Qwen)

Page 6 / 21← Newer Older →