AA Omniscience - Software Engineering (SWE) - C: leaderboard
C-language slice of AA Omniscience SWE, testing factual knowledge of C syntax, semantics, libraries, tooling, and engineering practice.
Metric: Accuracy (%). Source: artificialanalysis.ai. Saturation forecast: Around January 2027. 294 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Kimi K3 (Max) | 90 | #30 (Kimi K3) |
| 2 | Claude Opus 4.5 (Thinking) | 85 | #83 (Claude Opus 4.5) |
| 3 | Kimi K3 (Low) | 81 | #30 (Kimi K3) |
| 4 | Gemini 3 Pro (Preview) (High) | 78 | #66 (Gemini 3 Pro (Preview)) |
| 5 | Kimi K2.7 Code | 76 | #89 |
| 6 | Inkling (xHigh) | 75 | #126 (Inkling) |
| 7 | Kimi K2.6 | 74 | #104 |
| 8 | Claude Opus 4.5 (Non-reasoning) | 74 | #83 (Claude Opus 4.5) |
| 9 | DeepSeek V4 Pro (Reasoning, Max Effort) | 74 | #102 (DeepSeek V4 Pro) |
| 10 | Claude Sonnet 4.5 (Thinking) | 73 | #142 (Claude Sonnet 4.5) |
| 11 | Kimi K2.5 (Thinking) | 70 | #144 (Kimi K2.5) |
| 12 | DeepSeek V4 Flash (Reasoning, Max Effort) | 70 | #137 (DeepSeek V4 Flash) |
| 13 | Inkling Small | 69 | #138 |
| 14 | Qwen3.8 2.4T A95B | 68 | #55 |
| 15 | Nex N2 Pro | 67.35 | #107 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=aa-omniscience-software-engineering-swe-c · How It Works · Data refreshed daily, snapshot 2026-10-20.