Mmastodon Technology AI first seen 23 h ago, last 23 h ago, peak #1

LFM2.5-2.6B benchmark results circulate with independent verification

Original: LFM2.5-2.6B: GPQA 55.8%, HLE 6.2%, Long Context Reasoning 5.7%, SciCode 14.4%. All independently measured, not self-repo

Benchmark figures for the small language model LFM2.5-2.6B are drawing attention: 55.8% on GPQA, 6.2% on Humanity's Last Exam, 5.7% on long context reasoning and 14.4% on SciCode. Commenters highlight that these scores were independently measured rather than self-reported by the model's developers, lending the results more credibility. Discussion centres on how much capability a 2.6-billion-parameter model can pack in, and what that means for open-source AI.

Why now: The model's independently verified benchmark scores are strong for its small size, making the results notable in open-source AI circles.

LFM2.5-2.6B GPQA SciCode open source AI

Open on mastodon →

Evidence

LFM2.5-2.6B: GPQA 55.8%, HLE 6.2%, Long Context Reasoning 5.7%, SciCode 14.4%. All independently measured, not self-reported — so these bench numbers actually hold up. https:// olud.ai/leaderboard.html # LLM # Benchmarks # OpenSource # AI · opensourceaitech · 1

API: https://socialmediatrends-api.osmike.com/v1/trends/1933764