NVIDIA Nemotron 3.5 Super VL Card - SWE-bench Multilingual: leaderboard

NVIDIA Super 3.5 release card: SWE-bench Multilingual. Score (%) from the publisher's own evaluation table; source-specific task, offline and precision conditions remain separate. NeMo Gym / Evaluator reproduction; no copied reported peer cells.

Metric: Score (%). Source: huggingface.co. Saturation forecast: Around January 2027. 7 models tracked.

Top models

#ModelScoreOverall rank
1GLM-5.3 Flash78.3#66
2Qwen3.8-Flash-Next77.1#67
3DeepSeek V4 Flash (0731)72#75
4Inkling Small71.4#131
5Nemotron 3 Ultra68.8#238
6Qwen 3.5 122B A10B62#169

No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #7 Gemini 4 Argon.

Interactive version: theaggregate.ai/benchmark?slug=nvidia-nemotron-3-5-super-vl-card-swe-bench-multilingual · How It Works · Data refreshed daily, snapshot 2026-10-16.