# Step 3.7 Flash vs Trinity-Large-Thinking

> Side-by-side benchmark comparison for Step 3.7 Flash and Trinity-Large-Thinking across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/step-3-7-flash-vs-trinity-large-thinking
- Last updated: October 15, 2026

- Shared sourced benchmarks: 1
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Evidence is too thin for a benchmark verdict: Step 3.7 Flash and Trinity-Large-Thinking share only 1 sourced benchmark row.

## Summary

- Only 1 shared sourced benchmark row is available. That is not enough for a broad capability verdict, so this mirror does not name an overall winner.
- Trinity-Large-Thinking has the lower published output-token price.
- Trinity-Large-Thinking has the larger published context window at 512K.

## Model Snapshot

| Property | Step 3.7 Flash | Trinity-Large-Thinking |
|----------|----------|----------|
| Creator | StepFun | Arcee AI |
| Type | Open Weight | Open Weight |
| Reasoning | Reasoning | Reasoning |
| Context | 256K | 512K |
| Independent public score (not head-to-head) | 43.7 | 34.5 |
| Benchmarks Covered | 11 | 7 |
| Pricing (input/output) | $0.20 / $1.15 | $0.25 / $0.90 |

## Category Breakdown

### Agentic

- Winner: Insufficient shared evidence
- Step 3.7 Flash public-lane score: 37.1 (Estimated · #74/126)
- Trinity-Large-Thinking public-lane score: 13.5 (Estimated · #115/126)

| Benchmark | Step 3.7 Flash | Trinity-Large-Thinking | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.1 | 59.5% | Coming soon | Coming soon |
| BrowseComp | 75.8% | Coming soon | Coming soon |
| DeepSearchQA | 92.8% | Coming soon | Coming soon |
| Toolathlon | 49.5% | Coming soon | Coming soon |
| Claw-Eval | 67.1% | Coming soon | Coming soon |
| HLE w/ tools | 47.2% | Coming soon | Coming soon |
| Gert Labs | 51.57% | 32.55% | Step 3.7 Flash |
| τ²-bench Airline | Coming soon | 88.0% | Coming soon |

### Coding

- Winner: Insufficient shared evidence
- Step 3.7 Flash public-lane score: 30.2 (Estimated · #95/149)
- Trinity-Large-Thinking public-lane score: 17.9 (Supported · #123/149)

| Benchmark | Step 3.7 Flash | Trinity-Large-Thinking | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Pro | 56.3% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | 59.5% | Coming soon | Coming soon |
| SWE-bench Verified* | Coming soon | 63.2% | Coming soon |

### Reasoning

- Winner: Insufficient shared evidence
- Step 3.7 Flash public-lane score: 76.5 (Unranked · 2 rankable rows)
- Trinity-Large-Thinking public-lane score: 52 (Unranked · 2 rankable rows)

### Multimodal & Grounded

- Winner: Insufficient shared evidence
- Step 3.7 Flash public-lane score: 75.4 (Unranked · 3 rankable rows)
- Trinity-Large-Thinking public-lane score: Coming soon

| Benchmark | Step 3.7 Flash | Trinity-Large-Thinking | Winner |
|-----------|-----------|-----------|--------|
| SimpleVQA | 79.2% | Coming soon | Coming soon |
| V* | 95.3% | Coming soon | Coming soon |

### Knowledge

- Winner: Insufficient shared evidence
- Step 3.7 Flash public-lane score: 45 (Estimated · #96/182)
- Trinity-Large-Thinking public-lane score: 34.2 (Estimated · #135/182)

| Benchmark | Step 3.7 Flash | Trinity-Large-Thinking | Winner |
|-----------|-----------|-----------|--------|
| GPQA-D | Coming soon | 76.3% | Coming soon |
| MMLU-Pro (Arcee) | Coming soon | 83.4% | Coming soon |

### Instruction Following

- Winner: Insufficient shared evidence
- Step 3.7 Flash public-lane score: 82.1 (#54/146)
- Trinity-Large-Thinking public-lane score: 28.9 (#130/146)

| Benchmark | Step 3.7 Flash | Trinity-Large-Thinking | Winner |
|-----------|-----------|-----------|--------|
| IFBench | Coming soon | 52.3% | Coming soon |

### Mathematics

- Winner: Insufficient shared evidence
- Step 3.7 Flash public-lane score: Coming soon
- Trinity-Large-Thinking public-lane score: Coming soon

| Benchmark | Step 3.7 Flash | Trinity-Large-Thinking | Winner |
|-----------|-----------|-----------|--------|
| AIME25 (Arcee) | Coming soon | 96.3% | Coming soon |

## FAQ

### Is there enough evidence to pick between Step 3.7 Flash and Trinity-Large-Thinking?

Not yet. The models share only 1 sourced benchmark row, so this mirror reports the available measurements and metadata without naming a broad winner.

### What can I compare safely on this page?

Published pricing, context windows, model type, and individual shared benchmark rows are directly comparable. Independent overall scores and non-overlapping benchmark coverage are labeled separately and should not be read as a controlled head-to-head result.

## Related Comparisons

- [Step 3.7 Flash vs Trinity-Large-Preview](/compare/step-3-7-flash-vs-trinity-large-preview)
- [Trinity-Large-Thinking vs Trinity-Large-Preview](/compare/trinity-large-preview-vs-trinity-large-thinking)
- [Step 3.7 Flash vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-step-3-7-flash)
- [Trinity-Large-Thinking vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-trinity-large-thinking)

## Explore More

- [Step 3.7 Flash profile](/models/step-3-7-flash)
- [Trinity-Large-Thinking profile](/models/trinity-large-thinking)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)