Reflection Beam Safety - HPCT - 2026-07-09 - Exact Match: leaderboard
Practical knowledge about human pathogens,100 questions,exact-match multiple-response correctness; dated2026-07-09 release. Source-specific score; no fusion with a different harness or version is implied. Reflection Oct16 release links this technical report as its complete safety evaluations; final Beam model card links it too. Beam denotes final generic Beam1.0, numeric precision unreported; do not map to BF16, FP8 or NVFP4. Comparator names retained exactly as published; no provider/checkpoint/country/openness inference from abbreviated labels. Biological capability protocol: recommended sampling and highest available reasoning,65536 output tokens,256K context except Muse/GPTOSS128K; full benchmark3runs. Single-turn questions without tools/demos, agentic tasks in Inspect AI sandbox. Metric: Accuracy (%). Higher is better. Exact printed figure values; https://cdn.sanity.io/images/sp40emik/production/14ba9e6b965ac4937d83ddcc2814c17654bd1faf-2280x1890.png?w=3840&fit=max
Metric: Accuracy (%). Source: reflection.ai. Saturation forecast: Around 2028. 13 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Beam 1.0 | 61 | #97 |
| 2 | GLM-5.2 | 60.67 | #71 |
| 3 | Kimi K3 | 60 | #29 |
| 4 | Qwen 3.8 Max | 60 | #31 |
| 5 | DeepSeek V4.1 Flash | 60 | #35 |
| 6 | Kimi K2.6 | 59 | #105 |
| 7 | DeepSeek V4 Pro | 57.33 | #101 |
| 8 | GLM-5.3 | 56.67 | #40 |
| 9 | DeepSeek V4 Flash | 55.67 | #135 |
| 10 | Inkling | 55.33 | #123 |
| 11 | Nemotron 3 Ultra | 52 | #240 |
| 12 | GPT-OSS-120B | 51.33 | #336 |
| 13 | Muse Glimmer 30B | 48.33 | #178 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #7 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=reflection-beam-safety-hpct-2026-07-09-exact-match · How It Works · Data refreshed daily, snapshot 2026-10-17.