# Kimi K2.5 vs Trinity-Large-Thinking

> Side-by-side benchmark comparison for Kimi K2.5 and Trinity-Large-Thinking across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/kimi-k2-5-vs-trinity-large-thinking
- Last updated: September 29, 2026

- Shared sourced benchmarks: 5
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.7

## Quick Verdict

Pick Kimi K2.5 if you want the stronger benchmark profile. Trinity-Large-Thinking only makes more sense when its price, context window, or workload-specific category wins matter more than the overall score.

## Summary

- Kimi K2.5 leads overall 52.96 to 34.23.
- The clearest category separation is in agentic, where the averages are 36.3 for Kimi K2.5 and 17.7 for Trinity-Large-Thinking.
- The biggest single benchmark swing is Gert Labs in Agentic, with scores of 45.88% and 32.55%.
- Trinity-Large-Thinking is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.
- Trinity-Large-Thinking also has the larger context window at 512K.

## Model Snapshot

| Property | Kimi K2.5 | Trinity-Large-Thinking |
|----------|----------|----------|
| Creator | Moonshot AI | Arcee AI |
| Type | Open Weight | Open Weight |
| Reasoning | Non-Reasoning | Reasoning |
| Context | 256K | 512K |
| Overall Score | 52.96 | 34.23 |
| Benchmarks Covered | 45 | 5 |
| Pricing (input/output) | $0.60 / $3.00 | $0.25 / $0.90 |

## Category Breakdown

### Agentic

- Winner: Directional only
- Kimi K2.5 public-lane score: 36.3 (Estimated · #61/117)
- Trinity-Large-Thinking public-lane score: 17.7 (Estimated · #104/117)

| Benchmark | Kimi K2.5 | Trinity-Large-Thinking | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 50.8% | Coming soon | Coming soon |
| BrowseComp | 60.6% | Coming soon | Coming soon |
| Claw-Eval | 52.3% | Coming soon | Coming soon |
| QwenClawBench | 54.3% | Coming soon | Coming soon |
| τ³-bench results | 65.7% | Coming soon | Coming soon |
| DeepSearchQA | 77.1% | Coming soon | Coming soon |
| DeepPlanning | 14.4% | Coming soon | Coming soon |
| Toolathlon | 27.8% | Coming soon | Coming soon |
| MCP Atlas | 29.5% | Coming soon | Coming soon |
| MCP-Tasks | 59.1% | Coming soon | Coming soon |
| WideResearch | 72.7% | Coming soon | Coming soon |
| Gert Labs | 45.88% | 32.55% | Kimi K2.5 |
| ResearchClawBench | 14.0% | Coming soon | Coming soon |
| JobBench | 8.7% | Coming soon | Coming soon |

### Coding

- Winner: Directional only
- Kimi K2.5 public-lane score: 38.6 (Estimated · #66/142)
- Trinity-Large-Thinking public-lane score: 21 (Supported · #119/142)

| Benchmark | Kimi K2.5 | Trinity-Large-Thinking | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 76.8% | Coming soon | Coming soon |
| SWE-bench Verified* | 70.8% | 63.2% | Kimi K2.5 |
| LiveCodeBench v6 | 85.0% | Coming soon | Coming soon |
| SWE-bench Pro | 50.7% | Coming soon | Coming soon |
| SWE Multilingual | 73% | Coming soon | Coming soon |
| SWE-Rebench | 58.5% | Coming soon | Coming soon |
| React Native Evals | 77.2% | Coming soon | Coming soon |
| SciCode | 48.7% | Coming soon | Coming soon |

### Reasoning

- Winner: Not comparable
- Kimi K2.5 public-lane score: 55.2 (Unranked · 3 rankable rows)
- Trinity-Large-Thinking public-lane score: 48.3 (Unranked · 2 rankable rows)

| Benchmark | Kimi K2.5 | Trinity-Large-Thinking | Winner |
|-----------|-----------|-----------|--------|
| LongBench v2 | 61% | Coming soon | Coming soon |

### Multimodal & Grounded

- Winner: Not comparable
- Kimi K2.5 public-lane score: 66.8 (#25/50)
- Trinity-Large-Thinking public-lane score: Coming soon

| Benchmark | Kimi K2.5 | Trinity-Large-Thinking | Winner |
|-----------|-----------|-----------|--------|
| MMMU-Pro | 78.5% | Coming soon | Coming soon |
| Video-MME | 87.4% | Coming soon | Coming soon |
| MMVU | 80.4% | Coming soon | Coming soon |
| VideoMMMU | 86.6% | Coming soon | Coming soon |

### Knowledge

- Winner: Directional only
- Kimi K2.5 public-lane score: 47.9 (Estimated · #70/168)
- Trinity-Large-Thinking public-lane score: 35.9 (Estimated · #114/168)

| Benchmark | Kimi K2.5 | Trinity-Large-Thinking | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 87.6% | Coming soon | Coming soon |
| GPQA-D | 87.6% | 76.3% | Kimi K2.5 |
| SuperGPQA | 69.2% | Coming soon | Coming soon |
| MMLU-Pro | 87.1% | Coming soon | Coming soon |
| MMLU-Pro (Arcee) | 87.1% | 83.4% | Kimi K2.5 |
| HLE | 30.1% | Coming soon | Coming soon |

### Multilingual

- Winner: Not comparable
- Kimi K2.5 public-lane score: 38.2 (#8/12)
- Trinity-Large-Thinking public-lane score: Coming soon

| Benchmark | Kimi K2.5 | Trinity-Large-Thinking | Winner |
|-----------|-----------|-----------|--------|
| MMLU-ProX | 82.3% | Coming soon | Coming soon |
| NOVA-63 | 56.0% | Coming soon | Coming soon |

### Instruction Following

- Winner: Directional only
- Kimi K2.5 public-lane score: 84.4 (#41/124)
- Trinity-Large-Thinking public-lane score: 66.3 (#68/124)

| Benchmark | Kimi K2.5 | Trinity-Large-Thinking | Winner |
|-----------|-----------|-----------|--------|
| IFEval | 93.9% | Coming soon | Coming soon |

### Mathematics

- Winner: Not comparable
- Kimi K2.5 public-lane score: 62.1 (#4/7)
- Trinity-Large-Thinking public-lane score: Coming soon

| Benchmark | Kimi K2.5 | Trinity-Large-Thinking | Winner |
|-----------|-----------|-----------|--------|
| AIME 2025 | 96.1% | Coming soon | Coming soon |
| AIME26 | 95.8% | Coming soon | Coming soon |
| AIME25 (Arcee) | 96.3% | 96.3% | Tie |
| HMMT Feb 2025 | 95.4% | Coming soon | Coming soon |
| HMMT Nov 2025 | 91.1% | Coming soon | Coming soon |
| HMMT Feb 2026 | 87.1% | Coming soon | Coming soon |
| MMAnswerBench | 81.8% | Coming soon | Coming soon |
| FrontierMath v2 (Tiers 1-3) | 27.900% | Coming soon | Coming soon |
| FrontierMath v2 (Tier 4) | 4.200% | Coming soon | Coming soon |

## FAQ

### Which is better overall, Kimi K2.5 or Trinity-Large-Thinking?

Kimi K2.5 is ahead overall on BenchLM right now.

### Where is the biggest gap between Kimi K2.5 and Trinity-Large-Thinking?

The widest category gap is in agentic, where the averages are 36.3 for Kimi K2.5 and 17.7 for Trinity-Large-Thinking.

### How many benchmarks does Kimi K2.5 cover on BenchLM?

Kimi K2.5 currently has 45 sourced benchmark scores on BenchLM.

### How many benchmarks does Trinity-Large-Thinking cover on BenchLM?

Trinity-Large-Thinking currently has 5 sourced benchmark scores on BenchLM.

## Related Comparisons

- [Kimi K2.5 vs Kimi K2.5 (Reasoning)](/compare/kimi-k2-5-vs-kimi-k2-5-reasoning)
- [Trinity-Large-Thinking vs Kimi K2.5 (Reasoning)](/compare/kimi-k2-5-reasoning-vs-trinity-large-thinking)
- [Kimi K2.5 vs Trinity-Large-Preview](/compare/kimi-k2-5-vs-trinity-large-preview)
- [Trinity-Large-Thinking vs Trinity-Large-Preview](/compare/trinity-large-preview-vs-trinity-large-thinking)

## Explore More

- [Kimi K2.5 profile](/models/kimi-k2-5)
- [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)