AthenaBench - RCM: leaderboard

Map a vulnerability description to its CWE root cause, 2,000 items; exact-match accuracy.

Metric: Accuracy (%) mapping vulnerability descriptions to their CWE root cause (2,000 items). Source: raw.githubusercontent.com. Saturation forecast: Around February 2027. 10 models tracked. Updated 17 Nov 2026.

Top models

#ModelSettingScoreOverall rank
1GPT-571.6#177
2Gemini 2.5 Pro71.2#274
3Gemini 2.5 Flash65.1#467
4Llama 3.3 70B Instruct60#1387
5Llama 3 70B Instruct56.7#1689
6Llama-Primus-Merged56.6#2461
7Qwen 3 14BReasoning54.1#1264
8Qwen 3 8BThinking48.9#1868
9Qwen 3 4B 2507 Instruct45.4#2215
10Llama 3.1 8B Instruct42.8#4576

No result here: #1 Claude Fable 5.2, #2 GPT-6.2 Astra, #3 Gemini 4 Carbon.

Interactive version: theaggregate.ai/benchmark?slug=athenabench-rcm · How It Works · Data refreshed daily, snapshot 2026-11-17.