Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
1-bit Bonsai 4B
~44
0/8 categoriesGPT-5.2-Codex
82
Winner · 4/8 categories1-bit Bonsai 4B· GPT-5.2-Codex
Pick GPT-5.2-Codex if you want the stronger benchmark profile. 1-bit Bonsai 4B only becomes the better choice if you want the cheaper token bill or you would rather avoid the extra latency and token burn of a reasoning model.
GPT-5.2-Codex is clearly ahead on the aggregate, 82 to 44. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
GPT-5.2-Codex's sharpest advantage is in reasoning, where it averages 91.1 against 41.4. The single biggest benchmark swing on the page is GPQA, 28.7% to 97%.
GPT-5.2-Codex is also the more expensive model on tokens at $2.00 input / $8.00 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for 1-bit Bonsai 4B. That is roughly Infinityx on output cost alone. GPT-5.2-Codex is the reasoning model in the pair, while 1-bit Bonsai 4B is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. GPT-5.2-Codex gives you the larger context window at 400K, compared with 32K for 1-bit Bonsai 4B.
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 | 1-bit Bonsai 4B | GPT-5.2-Codex |
|---|---|---|
| Agentic | ||
| Terminal-Bench 2.0 | — | 90% |
| BrowseComp | — | 85% |
| OSWorld-Verified | — | 85% |
| Coding | ||
| HumanEval | — | 95% |
| SWE-bench Verified | — | 76% |
| LiveCodeBench | — | 66% |
| SWE-bench Pro | — | 86% |
| SWE-Rebench | — | 56.8% |
| Multimodal & Grounded | ||
| MMMU-Pro | — | 84% |
| OfficeQA Pro | — | 92% |
| ReasoningGPT-5.2-Codex wins | ||
| MuSR | 41.4% | 93% |
| BBH | — | 90% |
| LongBench v2 | — | 90% |
| MRCRv2 | — | 91% |
| KnowledgeGPT-5.2-Codex wins | ||
| GPQA | 28.7% | 97% |
| MMLU | — | 99% |
| SuperGPQA | — | 95% |
| HLE | — | 26% |
| FrontierScience | — | 86% |
| SimpleQA | — | 95% |
| Instruction FollowingGPT-5.2-Codex wins | ||
| IFEval | 69.6% | 92% |
| Multilingual | ||
| MGSM | — | 91% |
| MMLU-ProX | — | 87% |
| MathematicsGPT-5.2-Codex wins | ||
| MATH-500 | 65.8% | — |
| AIME 2023 | — | 99% |
| AIME 2024 | — | 99% |
| AIME 2025 | — | 98% |
| HMMT Feb 2023 | — | 95% |
| HMMT Feb 2024 | — | 97% |
| HMMT Feb 2025 | — | 96% |
| BRUMO 2025 | — | 96% |
GPT-5.2-Codex is ahead overall, 82 to 44. The biggest single separator in this matchup is GPQA, where the scores are 28.7% and 97%.
GPT-5.2-Codex has the edge for knowledge tasks in this comparison, averaging 72.9 versus 28.7. Inside this category, GPQA is the benchmark that creates the most daylight between them.
GPT-5.2-Codex has the edge for math in this comparison, averaging 97.1 versus 65.8. 1-bit Bonsai 4B stays close enough that the answer can still flip depending on your workload.
GPT-5.2-Codex has the edge for reasoning in this comparison, averaging 91.1 versus 41.4. Inside this category, MuSR is the benchmark that creates the most daylight between them.
GPT-5.2-Codex has the edge for instruction following in this comparison, averaging 92 versus 69.6. Inside this category, IFEval 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.