Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
1-bit Bonsai 8B
~50
0/8 categoriesClaude Sonnet 4.6
80
Winner · 4/8 categories1-bit Bonsai 8B· Claude Sonnet 4.6
Pick Claude Sonnet 4.6 if you want the stronger benchmark profile. 1-bit Bonsai 8B only becomes the better choice if you want the cheaper token bill.
Claude Sonnet 4.6 is clearly ahead on the aggregate, 80 to 50. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Claude Sonnet 4.6's sharpest advantage is in knowledge, where it averages 72.5 against 30. The single biggest benchmark swing on the page is GPQA, 30% to 89.9%.
Claude Sonnet 4.6 is also the more expensive model on tokens at $3.00 input / $15.00 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for 1-bit Bonsai 8B. That is roughly Infinityx on output cost alone. Claude Sonnet 4.6 gives you the larger context window at 200K, compared with 64K for 1-bit Bonsai 8B.
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 8B | Claude Sonnet 4.6 |
|---|---|---|
| Agentic | ||
| Terminal-Bench 2.0 | — | 59.1% |
| BrowseComp | — | 77% |
| OSWorld-Verified | — | 72.5% |
| Coding | ||
| HumanEval | — | 93% |
| SWE-bench Verified | — | 79.6% |
| LiveCodeBench | — | 54% |
| SWE-bench Pro | — | 64% |
| FLTEval | — | 23.7% |
| SWE-Rebench | — | 60.7% |
| React Native Evals | — | 77.9% |
| Multimodal & Grounded | ||
| OfficeQA Pro | — | 88% |
| ReasoningClaude Sonnet 4.6 wins | ||
| MuSR | 50% | 93% |
| BBH | — | 88% |
| LongBench v2 | — | 83% |
| MRCRv2 | — | 79% |
| ARC-AGI-2 | — | 59% |
| KnowledgeClaude Sonnet 4.6 wins | ||
| GPQA | 30% | 89.9% |
| SuperGPQA | — | 95% |
| MMLU-Pro | — | 79.2% |
| HLE | — | 49% |
| FrontierScience | — | 85% |
| SimpleQA | — | 48.5% |
| Instruction FollowingClaude Sonnet 4.6 wins | ||
| IFEval | 79.8% | 89.5% |
| Multilingual | ||
| MGSM | — | 91% |
| MMLU-ProX | — | 89% |
| MathematicsClaude Sonnet 4.6 wins | ||
| MATH-500 | 66% | 97.8% |
Claude Sonnet 4.6 is ahead overall, 80 to 50. The biggest single separator in this matchup is GPQA, where the scores are 30% and 89.9%.
Claude Sonnet 4.6 has the edge for knowledge tasks in this comparison, averaging 72.5 versus 30. Inside this category, GPQA is the benchmark that creates the most daylight between them.
Claude Sonnet 4.6 has the edge for math in this comparison, averaging 97.8 versus 66. Inside this category, MATH-500 is the benchmark that creates the most daylight between them.
Claude Sonnet 4.6 has the edge for reasoning in this comparison, averaging 78 versus 50. Inside this category, MuSR is the benchmark that creates the most daylight between them.
Claude Sonnet 4.6 has the edge for instruction following in this comparison, averaging 89.5 versus 79.8. 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.