# dots3-note Preview vs Flint

> Side-by-side benchmark comparison for dots3-note Preview and Flint across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/dots3-note-preview-vs-flint-40b-a2-5b
- Last updated: October 20, 2026

- Shared sourced benchmarks: 5
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Flint leads by point estimate. Conditional score ranges do not establish rank confidence. Choose using the category evidence and your own workload tests.

## Summary

- Flint has the higher overall point estimate 67 to 63.93. Conditional score ranges do not establish rank confidence.
- The clearest category separation is in instruction following, where the averages are 89.1 for dots3-note Preview and 94.7 for Flint.
- The biggest single benchmark swing is Terminal-Bench 2.1 in Agentic, with scores of 75.1% and 54.9%.
- dots3-note Preview also has the larger context window at 512K.

## Model Snapshot

| Property | dots3-note Preview | Flint |
|----------|----------|----------|
| Creator | Dots Studio | Recursive |
| Type | Open Weight | Open Weight |
| Reasoning | Reasoning | Reasoning |
| Context | 512K | 256K |
| Overall Score | 63.93 | null |
| Benchmarks Covered | 31 | 5 |
| Pricing (input/output) | $0.00 / $0.00 | $0.00 / $0.00 |

## Category Breakdown

### Agentic

- Winner: Not comparable
- dots3-note Preview public-lane score: 59.4 (Estimated · #30/132)
- Flint public-lane score: Coming soon

| Benchmark | dots3-note Preview | Flint | Winner |
|-----------|-----------|-----------|--------|
| Claw-Eval | 73.4% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | 75.1% | 54.9% | dots3-note Preview |
| Toolathlon-Verified | 55.6% | Coming soon | Coming soon |
| skillsBench | 52.8% | Coming soon | Coming soon |
| APEX-Agents | 30.8% | Coming soon | Coming soon |
| BrowseComp | 83.3% | Coming soon | Coming soon |
| HLE w/ tools | 52.6% | Coming soon | Coming soon |
| DeepSearchQA | 92.1% | Coming soon | Coming soon |
| WideResearch | 78.9% | Coming soon | Coming soon |

### Coding

- Winner: Not comparable
- dots3-note Preview public-lane score: Coming soon
- Flint public-lane score: Coming soon

| Benchmark | dots3-note Preview | Flint | Winner |
|-----------|-----------|-----------|--------|
| Codeforces | 3056.0 | Coming soon | Coming soon |
| LiveCodeBench v6 | 91.5% | 80.3% | dots3-note Preview |
| Terminal-Bench 2.1 | 75.1% | Coming soon | Coming soon |
| SWE-bench Verified | 78.4% | 74.2% | dots3-note Preview |
| SWE Multilingual | 75.7% | Coming soon | Coming soon |
| SWE-bench Pro | 61% | Coming soon | Coming soon |
| NL2Repo | 49.8% | Coming soon | Coming soon |

### Reasoning

- Winner: Not comparable
- dots3-note Preview public-lane score: 76.6 (Unranked · 1 rankable row)
- Flint public-lane score: Coming soon

| Benchmark | dots3-note Preview | Flint | Winner |
|-----------|-----------|-----------|--------|
| ARC-AGI-2 | 81.4% | Coming soon | Coming soon |

### Multimodal & Grounded

- Winner: Not comparable
- dots3-note Preview public-lane score: 79.6 (Unranked · 10 rankable rows)
- Flint public-lane score: Coming soon

| Benchmark | dots3-note Preview | Flint | Winner |
|-----------|-----------|-----------|--------|
| SimpleVQA | 72.5% | Coming soon | Coming soon |
| MMMU-Pro | 79.1% | Coming soon | Coming soon |
| MathVision | 87.7% | Coming soon | Coming soon |
| ZeroBench | 19.0% | Coming soon | Coming soon |
| CharXiv w/o tools | 83.1% | Coming soon | Coming soon |
| GDP.pdf (no tools) | 60.7% | Coming soon | Coming soon |
| PerceptionBench | 53.4% | Coming soon | Coming soon |
| BabyVision | 50.0% | Coming soon | Coming soon |
| MMVU | 79.9% | Coming soon | Coming soon |
| VideoMMMU | 86.8% | Coming soon | Coming soon |

### Knowledge

- Winner: Not comparable
- dots3-note Preview public-lane score: Coming soon
- Flint public-lane score: Coming soon

| Benchmark | dots3-note Preview | Flint | Winner |
|-----------|-----------|-----------|--------|
| HLE | 52.6% | Coming soon | Coming soon |

### Instruction Following

- Winner: Flint
- dots3-note Preview public-lane score: 89.1 (#34/152)
- Flint public-lane score: 94.7 (#3/152)

| Benchmark | dots3-note Preview | Flint | Winner |
|-----------|-----------|-----------|--------|
| IFBench | 80.4% | 89.2% | Flint |
| IFEval | 93.9% | 95.1% | Flint |

### Mathematics

- Winner: Not comparable
- dots3-note Preview public-lane score: Coming soon
- Flint public-lane score: Coming soon

| Benchmark | dots3-note Preview | Flint | Winner |
|-----------|-----------|-----------|--------|
| IMOAnswerBench | 90.9% | Coming soon | Coming soon |

## FAQ

### Which is better overall, dots3-note Preview or Flint?

Flint has the higher overall point estimate. Conditional score ranges do not establish rank confidence.

### Where is the biggest gap between dots3-note Preview and Flint?

The widest category gap is in instruction following, where the averages are 89.1 for dots3-note Preview and 94.7 for Flint.

### How many benchmarks does dots3-note Preview cover on BenchLM?

dots3-note Preview currently has 31 sourced benchmark scores on BenchLM.

### How many benchmarks does Flint cover on BenchLM?

Flint currently has 5 sourced benchmark scores on BenchLM.

## Related Comparisons

- [dots3-note Preview vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-dots3-note-preview)
- [Flint vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-flint-40b-a2-5b)
- [dots3-note Preview vs GPT-6.1 Sol](/compare/dots3-note-preview-vs-gpt-6-1-sol)
- [Flint vs GPT-6.1 Sol](/compare/flint-40b-a2-5b-vs-gpt-6-1-sol)

## Explore More

- [dots3-note Preview profile](/models/dots3-note-preview)
- [Flint profile](/models/flint-40b-a2-5b)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)