Reflection 首个模型 Beam 登上美国开源权重模型第二位
Reflection 的第一个开源模型 Beam 出来了，501B 参数只激活 23B，跑分超过 NVIDIA 和 K2 Horizon，但幻觉率有点高，终端任务也比较弱。
Reflection AI 发布首个开源权重模型 Beam，在 Artificial Analysis Intelligence Index 上得 30 分，位列美国开源权重模型第二，仅次于 Meta 的 Muse Spark Open（39 分），领先 NVIDIA Nemotron 3.5 Super VL（26 分）。Beam 总参数 501B、激活参数 23B，已在 Hugging Face 上线，上下文窗口 100 万 tokens。它在 AutomationBench-AA 拿到 48.5%，比 K2 Horizon 高 11 个百分点，但 Terminal-Bench 4.0 仅得 3.0%，是明显短板。该模型幻觉率达 47%，高于 K2 Horizon 的 26% 和 Qwen3.8 27B 的 30%。
Reflection’s first model, Beam, scores 30 on the Artificial Analysis Intelligence Index, placing it #2 among US open weights models
Beam is an open weights model with 501B total and 23B active parameters, released on @huggingface
Congratulations to @reflection_ai on the release!
Key takeaways:
➤ Second among US open weights models: Beam scores 30, behind only Meta's Muse Spark Open (39) and ahead of yesterday’s NVIDIA Nemotron 3.5 Super VL (26) release. Outside China, only Muse Spark Open and the UAE's K2 Horizon (31) score higher
➤ Token efficient for its intelligence: Beam uses ~26k output tokens per Intelligence Index task compared to K2 Horizon, one point ahead, which uses twice as many (~52k). Proprietary models still set the frontier, with GPT-6 Astra (max) scoring 53 on the same budget (~27k)
➤ Strong on agentic workflows, weaker in the terminal: Beam scores 48.5% on AutomationBench-AA, 11 percentage points ahead of K2 Horizon (37.2%) and level with Qwen3.8 27B (48.2%). Terminal-Bench 4.0 is a weak point, where Beam scores 3.0%, behind Qwen3.8 27B (5.6%) and Muse Spark Open (8.1%)
➤ Knows more, guesses more: On AA-Omniscience it answers 33% of questions correctly, well ahead of K2 Horizon (18%) and Qwen3.8 27B (16%). But its hallucination rate is 47%, against 26% for K2 Horizon and 30% for Qwen3.8 27B, giving Beam a net index score of 1.5, ahead of both peers (−3.0 and −10.0)
Other model details Context window: 1M tokens Modalities: Text Parameters: 501B / 23B
