K2 Horizon MoVA Card - SciCode: leaderboard
SciCode: the model writes code for subproblems taken from natural-science research tasks, checked against test cases. Scores in percent from IFM's K2 Horizon MoVA 36B A4B model card, which states that all reported MoVA results use high reasoning effort. The card takes its six baseline scores from Artificial Analysis (Muse Glimmer-30B at high reasoning effort, the other open models in reasoning mode), so this table mixes IFM's MoVA result with copied third-party numbers and is separate from Artificial Analysis's own SciCode board.
Metric: Score (%). Source: huggingface.co. Saturation forecast: Around February 2027. 7 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Muse Glimmer 30B (High) | 43.6 | #371 (Muse Glimmer 30B) |
| 2 | Gemma 4 31B (IT) (Reasoning) | 43.4 | #343 (Gemma 4 31B (IT)) |
| 3 | Qwen 3.6 35B A3B (Reasoning) | 35.8 | #461 (Qwen 3.6 35B A3B) |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=k2-horizon-mova-card-scicode · How It Works · Data refreshed daily, snapshot 2026-11-12.