Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
GLM-5V-Turbo
~58
Winner · 1/8 categoriesNemotron 3 Super 100B
57
0/8 categoriesGLM-5V-Turbo· Nemotron 3 Super 100B
Pick GLM-5V-Turbo if you want the stronger benchmark profile. Nemotron 3 Super 100B only becomes the better choice if you want the cheaper token bill or you need the larger 1M context window.
GLM-5V-Turbo finishes one point ahead overall, 58 to 57. That is enough to call, but not enough to treat as a blowout. This matchup comes down to a few meaningful edges rather than one model dominating the board.
GLM-5V-Turbo's sharpest advantage is in agentic, where it averages 58 against 56.6. The single biggest benchmark swing on the page is BrowseComp, 51.9% to 61%.
GLM-5V-Turbo is also the more expensive model on tokens at $1.20 input / $4.00 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for Nemotron 3 Super 100B. That is roughly Infinityx on output cost alone. Nemotron 3 Super 100B gives you the larger context window at 1M, compared with 200K for GLM-5V-Turbo.
BenchLM keeps the benchmark table and the operator tradeoffs on the same page so a better score does not hide a materially slower, pricier, or smaller-context model.
Runtime metrics show N/A when BenchLM does not have a sourced snapshot for that exact model. The scoring rules and freshness policy are documented on the methodology page.
| Benchmark | GLM-5V-Turbo | Nemotron 3 Super 100B |
|---|---|---|
| AgenticGLM-5V-Turbo wins | ||
| BrowseComp | 51.9% | 61% |
| OSWorld-Verified | 62.3% | 54% |
| BrowseComp-VL | 51.9% | — |
| OSWorld | 62.3% | — |
| AndroidWorld | 75.7% | — |
| WebVoyager | 88.5% | — |
| Terminal-Bench 2.0 | — | 56% |
| Coding | ||
| HumanEval | — | 57% |
| SWE-bench Verified | — | 44% |
| LiveCodeBench | — | 38% |
| SWE-bench Pro | — | 44% |
| Multimodal & Grounded | ||
| Design2Code | 94.8% | — |
| Flame-VLM-Code | 93.8% | — |
| Vision2Web | 31.0% | — |
| ImageMining | 30.7% | — |
| MMSearch | 72.9% | — |
| MMSearch-Plus | 30.0% | — |
| SimpleVQA | 78.2% | — |
| Facts-VLM | 58.6% | — |
| V* | 89.0% | — |
| MMMU-Pro | — | 55% |
| OfficeQA Pro | — | 67% |
| Reasoning | ||
| MuSR | — | 60% |
| BBH | — | 83% |
| LongBench v2 | — | 75% |
| MRCRv2 | — | 75% |
| Knowledge | ||
| MMLU | — | 65% |
| GPQA | — | 64% |
| SuperGPQA | — | 62% |
| MMLU-Pro | — | 72% |
| HLE | — | 13% |
| FrontierScience | — | 63% |
| SimpleQA | — | 62% |
| Instruction Following | ||
| IFEval | — | 84% |
| Multilingual | ||
| MGSM | — | 84% |
| MMLU-ProX | — | 77% |
| Mathematics | ||
| AIME 2023 | — | 65% |
| AIME 2024 | — | 67% |
| AIME 2025 | — | 66% |
| HMMT Feb 2023 | — | 61% |
| HMMT Feb 2024 | — | 63% |
| HMMT Feb 2025 | — | 62% |
| BRUMO 2025 | — | 64% |
| MATH-500 | — | 83% |
GLM-5V-Turbo is ahead overall, 58 to 57. The biggest single separator in this matchup is BrowseComp, where the scores are 51.9% and 61%.
GLM-5V-Turbo has the edge for agentic tasks in this comparison, averaging 58 versus 56.6. Inside this category, BrowseComp is the benchmark that creates the most daylight between them.
Get notified when new models drop, benchmark scores change, or the leaderboard shifts. One email per week.
Free. No spam. Unsubscribe anytime. We only store derived location metadata for consent routing.