BlogLLM Benchmark Scores as Published, Side by Side
LMArena v3 proxy: Results as Published
Every result the catalog holds for LMArena v3 proxy: 7 models from 5 developers, read from 1 page. Each number is as printed by the company named beside it; nothing is ranked or rescored. Models are listed by developer, newest first.
Area Writing and ConversationMaintainer NVIDIA (as printed)Introduced 2026Data version 2026103001, as of 2026-10-30
LMArena v3 proxy is printed on the NVIDIA Nemotron 3.5 Super VL model card among the conversational results; the card does not describe it. By its name it is an offline stand-in for LMArena human preference, scored by an automatic judge.
Not checked against a maintainer's page.
LMArena v3 proxy
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| DeepSeek-V4-Flash-0731DeepSeek | 49.8 | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
| Qwen3.5-122B-A10BAlibaba, released 2026-02-24 | 47 | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
| Qwen3.8-Flash-NextAlibaba | 35.2 | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
| GLM-5.3-FlashZ.ai, released 2026-08-26 | 61 | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
| Nemotron 3.5 Super VL 120B-A12BNVIDIA, released 2026-10-15 | 52.67 | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
| Nemotron 3 UltraNVIDIA, released 2026-06-04 | 34.3 | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
| Inkling-SmallThinking Machines | 53.6 | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
Every number here is read from the same catalog file as the benchmark table, data version 2026103001, and is the number the table shows for that model and test. Where one page printed a model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.