ScienceArena - IBO 2023: leaderboard
Metric: Score (out of 453): points on the International Biology Olympiad 2023 objective items, text-only question renderings, answered with the dedicated IBO runner and scored deterministically against the official answer key. Source: arxiv.org. Saturation forecast: Estimated already saturated. 14 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 431 |
| 2 | Gemini 3.5 Flash | 430 |
| 3 | Gemini 3 Flash | 428 |
| 4 | GPT-5.5 | 415 |
| 5 | Seed 2.0 Pro | 415 |
| 6 | Qwen 3.6 Plus | 413 |
| 7 | Claude Opus 4.7 | 407 |
| 8 | GPT-5.4 | 358 |
| 9 | GLM-5.1 | 349 |
| 10 | Qwen 3.7 Max | 349 |
| 11 | MiniMax-M2.7 | 337 |
| 12 | DeepSeek V4 Pro | 327 |
| 13 | DeepSeek V4 Flash | 324 |
| 14 | MiMo-V2.5-Pro | 317 |
Interactive version: theaggregate.ai/benchmark?slug=sciencearena-ibo-2023 · How It Works · Data refreshed daily, snapshot 2026-09-29.