Reflection Beam 1.0 benchmarks
Reflection Beam 1.0 has 11 published scores in this dataset, from a Reflection AI release dated 2026-10-16. Its composite index is 87.0, which places it 10th of 22 ranked models and 6th among 15 open-weight models. Its strongest area is knowledge (index 97.4) and its weakest is agentic (index 78.2). Its best placing is on AIME, where its 97.7 ranks 1st of 5 models with a published score.
Category profile
Index 0–100: each score relative to the best published score on that test.
Model facts
- Lab
- Reflection AI
- Type
- Open weights
- Released
- 2026-10-16
- Parameters
- 501B total, 23B active (MoE)
- Context
- 1M
- License
- Apache 2.0
Reflection Beam 1.0 hardware requirements and cost
Even at 4-bit it needs about 346 GB (4× H200 (564 GB)), well beyond a home workstation, so most people run it on rented multi-GPU servers. Full BF16 precision needs about 1.2 TB (Multiple nodes (over 1.1 TB)).
| Precision | Weights | With headroom | Smallest setup |
|---|---|---|---|
| BF16 (full precision) | 1.0 TB | 1.2 TB | Multiple nodes (over 1.1 TB) |
| FP8 / 8-bit | 501 GB | 576 GB | 8× H100 (640 GB) |
| 4-bit (GGUF Q4_K_M) | 301 GB | 346 GB | 4× H200 (564 GB) |
Estimate: parameters × bytes per parameter, plus 15% for the KV cache and runtime at modest context lengths. Long contexts and large batches need more.
Lighter or stronger open models
Open models ranked just above and below on the composite index, with their 4-bit memory needs.
- Kimi K390.61.9 TB
- Tencent Hy4 Preview89.9531 GB
- Muse Spark Open88.0563 GB
- Qwen3.6 27B85.819 GB
- Qwen3.8 27B83.219 GB
- GLM 5.382.7520 GB
Reflection Beam 1.0 speed and pricing
Measured figures link to their source; estimates are labelled.
- API output speed
- 371 tok/sArtificial Analysis median · Artificial Analysis
- Time to first token
- 0.37 sOpenRouter model page provider stats
- API price per 1M tokens
- $0.250 in · $1.00 outcheapest provider on OpenRouter: Nebius · OpenRouter endpoints API
Score by test
Rank is among every model with a published score on that test.
Nearby in the composite ranking
Models with the closest composite index.
Head-to-head comparisons
Side-by-side pages built from the tests both models report.
No head-to-head page for Reflection Beam 1.0 yet. Compare it on the rankings dashboard.
Sources
Scores are published results from model cards, lab reports, and public leaderboards, each linked to its source. Settings such as thinking mode or test version differ between sources and are shown next to each score. OpenLLM Buddy catalog models are uncensored fine-tunes; their scores are those of the official base model. Data collected 2026-10-30. How the index works