Benchmark
BeyondAIME Benchmark
What is BeyondAIME?
Beyond AIME difficulty competition math; most models score low and gaps are dominated by run-to-run variance. Benchmark Radar tracks 3 reported scores for…
- Evaluates
- math
- Openness
- unknown
- Catalog source
- Model reports
- Reported scores
- 3
BeyondAIME links
BeyondAIME results and reported scores
Model reports
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Seed2.0 Lite | ByteDance | 76.0 | 2026-02-14 | evidence |
| Seed2.0 Mini | ByteDance | 69.0 | 2026-02-14 | evidence |
| Seed2.0 Pro | ByteDance | 86.5 | 2026-02-14 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.
Which sources cite BeyondAIME?
- Seed2.0 (Pro / Lite / Mini) ByteDance, 2026-02-14