Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
GLM-5V-Turbo
~58
Winner · 1/8 categoriesGPT-4o
51
0/8 categoriesGLM-5V-Turbo· GPT-4o
Pick GLM-5V-Turbo if you want the stronger benchmark profile. GPT-4o only becomes the better choice if its workflow or ecosystem matters more than the raw scoreboard.
GLM-5V-Turbo is clearly ahead on the aggregate, 58 to 51. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
GLM-5V-Turbo's sharpest advantage is in agentic, where it averages 58 against 51.2. The single biggest benchmark swing on the page is OSWorld-Verified, 62.3% to 48%.
GPT-4o is also the more expensive model on tokens at $2.50 input / $10.00 output per 1M tokens, versus $1.20 input / $4.00 output per 1M tokens for GLM-5V-Turbo. That is roughly 2.5x on output cost alone. GLM-5V-Turbo gives you the larger context window at 200K, compared with 128K for GPT-4o.
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 | GPT-4o |
|---|---|---|
| AgenticGLM-5V-Turbo wins | ||
| BrowseComp | 51.9% | 59% |
| OSWorld-Verified | 62.3% | 48% |
| BrowseComp-VL | 51.9% | — |
| OSWorld | 62.3% | — |
| AndroidWorld | 75.7% | — |
| WebVoyager | 88.5% | — |
| Terminal-Bench 2.0 | — | 49% |
| Coding | ||
| HumanEval | — | 58% |
| SWE-bench Verified | — | 20% |
| LiveCodeBench | — | 38% |
| SWE-bench Pro | — | 29% |
| 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 | — | 74% |
| OfficeQA Pro | — | 70% |
| Reasoning | ||
| MuSR | — | 62% |
| BBH | — | 82% |
| LongBench v2 | — | 62% |
| MRCRv2 | — | 63% |
| Knowledge | ||
| MMLU | — | 66% |
| GPQA | — | 66% |
| SuperGPQA | — | 64% |
| MMLU-Pro | — | 64% |
| HLE | — | 1% |
| FrontierScience | — | 58% |
| SimpleQA | — | 64% |
| Instruction Following | ||
| IFEval | — | 82% |
| Multilingual | ||
| MGSM | — | 82% |
| MMLU-ProX | — | 72% |
| Mathematics | ||
| AIME 2023 | — | 66% |
| AIME 2024 | — | 68% |
| AIME 2025 | — | 67% |
| HMMT Feb 2023 | — | 62% |
| HMMT Feb 2024 | — | 64% |
| HMMT Feb 2025 | — | 63% |
| BRUMO 2025 | — | 65% |
| MATH-500 | — | 80% |
GLM-5V-Turbo is ahead overall, 58 to 51. The biggest single separator in this matchup is OSWorld-Verified, where the scores are 62.3% and 48%.
GLM-5V-Turbo has the edge for agentic tasks in this comparison, averaging 58 versus 51.2. Inside this category, OSWorld-Verified 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.