Model comparison
Step 3.7 Flash vs Trinity-Large-Preview
Head-to-head evidence from 15 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
BenchAlign evidence: Step 3.7 Flash estimated; Trinity-Large-Preview estimated. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. Step 3.7 Flash and Trinity-Large-Preview share 15 comparable benchmark results. 0 of 8 categories are comparable. 15 results are unique to Step 3.7 Flash; 4 to Trinity-Large-Preview.
Updated July 16, 2026- Shared results
- 15
- Step 3.7 Flash only
- 15
- Trinity-Large-Preview only
- 4
- Comparable categories
- 0 / 8
Benchmark data for Step 3.7 Flash and Trinity-Large-Preview is coming soon on BenchLM.
Confidence note. This is a partial-evidence comparison with 15 shared benchmark results across 6 evidence categories; 0 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
BenchLM has partial data for these models, but not enough overlapping benchmark coverage to produce a fair score-level comparison yet.
Step 3.7 Flash is priced at $0.20 input / $1.15 output per 1M tokens, versus $0.25 input / $1.00 output per 1M tokens for Trinity-Large-Preview. Trinity-Large-Preview has the larger context window at 512K, compared with 256K for Step 3.7 Flash.
Category breakdown
Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.
| Category | Step 3.7 Flash | Δ | Trinity-Large-Preview |
|---|---|---|---|
| Agentic | Step 3.7 Flash66.4 | MarginNo overlap | Trinity-Large-PreviewNot measured |
| Coding | Step 3.7 Flash56.3 | MarginNo overlap | Trinity-Large-PreviewNot measured |
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | Step 3.7 Flash | Trinity-Large-Preview | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Step 3.7 Flash$0.2 input / $1.15 output | Trinity-Large-Preview$0.25 input / $1 output | Trinity-Large-Preview has the lower combined listed price. |
| Generation speedtokens per second | Step 3.7 FlashNot available | Trinity-Large-PreviewNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | Step 3.7 FlashNot available | Trinity-Large-PreviewNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | Step 3.7 Flash256K | Trinity-Large-Preview512K | Trinity-Large-Preview lists the larger context window. |
Benchmark Deep Dive
Agentic12 benchmarks
| Benchmark | Step 3.7 Flash | Trinity-Large-Preview | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 59.5% | — | Not comparable |
| BrowseCompSource | 75.8% | — | Not comparable |
| DeepSearchQASource | 92.8% | — | Not comparable |
| GDPval-AASource | 25.9% | 2.7% | Step 3.7 Flash leads |
| ToolathlonSource | 49.5% | — | Not comparable |
| Claw-EvalSource | 67.1% | — | Not comparable |
| HLE w/ toolsSource | 47.2% | — | Not comparable |
| Gert LabsSource | 51.57% | — | Not comparable |
| AA Agentic IndexSource | 21.5% | — | Not comparable |
| τ²-bench resultsSource | 98.5% | 90.1% | Step 3.7 Flash leads |
| GDPval-AASource | 1017 | 554 | Step 3.7 Flash leads |
| APEX-Agents-AASource | 14.8% | — | Not comparable |
Coding5 benchmarks
Reasoning2 benchmarks
Knowledge9 benchmarks
| Benchmark | Step 3.7 Flash | Trinity-Large-Preview | Result |
|---|---|---|---|
| Artificial Analysis Intelligence IndexSource | 30.3% | 24.5% | Step 3.7 Flash leads |
| AA-GPQA DiamondSource | 80.9% | 75.2% | Step 3.7 Flash leads |
| AA-HLESource | 19.9% | 14.7% | Step 3.7 Flash leads |
| AA-Omniscience IndexSource | -37.5% | -44.2% | Step 3.7 Flash leads |
| AA-Omniscience AccuracySource | 25.4% | 22.8% | Step 3.7 Flash leads |
| AA-Omniscience Hallucination RateSource | 84.4% | 86.6% | Step 3.7 Flash leads |
| MMLUSource | — | 87.2% | Not comparable |
| MMLU-Pro (Arcee)Source | — | 75.2% | Not comparable |
| GPQA-DSource | — | 63.3% | Not comparable |
Math1 benchmarks
| Benchmark | Step 3.7 Flash | Trinity-Large-Preview | Result |
|---|---|---|---|
| AIME25 (Arcee)Source | — | 24.0% | Not comparable |
Multimodal4 benchmarks
Inst. Following1 benchmarks
| Benchmark | Step 3.7 Flash | Trinity-Large-Preview | Result |
|---|---|---|---|
| AA-IFBenchSource | 67.3% | 56.3% | Step 3.7 Flash leads |
Frequently Asked Questions (3)
Can I compare Step 3.7 Flash and Trinity-Large-Preview on BenchLM yet?
Not fully yet. BenchLM is tracking both models, but the sourced benchmark breakdown for this comparison is still coming soon.
Why does this comparison show “coming soon”?
BenchLM only shows category winners and benchmark-level calls when we have sourced results that can be compared fairly. For these models, the public benchmark coverage is not complete enough yet.
What data is available for Step 3.7 Flash and Trinity-Large-Preview today?
Step 3.7 Flash: $0.20 input / $1.15 output per 1M tokens Trinity-Large-Preview: $0.25 input / $1.00 output per 1M tokens Both model pages still include creator, context window, reasoning mode, and other metadata while benchmark coverage fills in.
Related Comparisons
Explore More
The AI models change fast. We track them for you.
A weekly brief for engineers and researchers covering new models, ranking shifts, and pricing changes.
Free. No spam. Unsubscribe anytime.