Model comparison
Kimi K2.7 Code vs Trinity Large Thinking
Kimi K2.7 Code is the stronger model overall, scoring 43.3 to 38.6 on the Noometry Index. Trinity Large Thinking costs 4.4× less per token, which makes it the better buy when Kimi K2.7 Code's lead doesn't matter for your workload.
Last verified . 4 shared benchmarks.
Arcee AISummary
- They share 4 benchmarks with published results for both. Kimi K2.7 Code scores higher in 4 categories and Trinity Large Thinking in 0 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Kimi K2.7 Code leads 39.0 to 16.9.
- The biggest single-benchmark swing is Surface Evolver Bench: 48.8% for Kimi K2.7 Code and 15.6% for Trinity Large Thinking.
- Trinity Large Thinking is cheaper at $0.25 / $0.80 per million input/output tokens, against $0.95 / $4 for Kimi K2.7 Code.
Side by side
| Kimi K2.7 Code | Trinity Large Thinking | |
|---|---|---|
| Provider | Moonshot AI | Arcee AI |
| Noometry Index | 43.3 | 38.6 |
| Released | 2026-06-12 | 2026-04-01 |
| Weights | Open | Open |
| Context window | 262K | 262K |
| Max output | 262K | 80K |
| Input $ / M tokens | $0.95 | $0.25 |
| Output $ / M tokens | $4 | $0.80 |
| Results tracked | 19 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.7 Code leads
Kimi K2.7 Code: 42.9 (#95), Trinity Large Thinking: 34.1 (#244)
| Benchmark | Kimi K2.7 Code | Trinity Large Thinking |
|---|---|---|
| LMArena WebDev | 1473 | 1238 |
| SciCode | 47.5% | 36.1% |
| DeepSWE | 30.5% | — |
| FrontierCode | 30.1% | — |
| WeirdML | 54.1% | — |
| LMArena Coding | — | 1381 |
| ALE-Bench | 886.23 | — |
Agentic & Tool Use Not comparable
Kimi K2.7 Code: 24.0 (#122), Trinity Large Thinking: —
| Benchmark | Kimi K2.7 Code | Trinity Large Thinking |
|---|---|---|
| APEX-Agents | 37.6% | — |
| GBAEval | 0.9% | — |
| Vending-Bench 2 | 5,083 | — |
Reasoning Kimi K2.7 Code leads
Kimi K2.7 Code: 39.0 (#61), Trinity Large Thinking: 16.9 (#298)
| Benchmark | Kimi K2.7 Code | Trinity Large Thinking |
|---|---|---|
| CritPt | 10% | 0.9% |
| Surface Evolver Bench | 48.8% | 15.6% |
| SimpleBench | 57.9% | — |
| NYT Connections (extended) | — | 16.5% |
| Chess Puzzles | 21% | — |
| Thematic Generalization | — | 41.6% |
| LMArena Hard Prompts | — | 1350 |
| Epoch Capabilities Index | 149.97 | — |
Math Kimi K2.7 Code leads
Kimi K2.7 Code: 52.9 (#48), Trinity Large Thinking: 37.6 (#149)
| Benchmark | Kimi K2.7 Code | Trinity Large Thinking |
|---|---|---|
| FrontierMath (Tiers 1-3) | 54% | — |
| FrontierMath Tier 4 | 12.2% | — |
| OTIS Mock AIME 2024-2025 | 95.6% | — |
| LMArena Math | — | 1366 |
Knowledge Kimi K2.7 Code leads
Kimi K2.7 Code: 53.5 (#57), Trinity Large Thinking: 40.9 (#113)
| Benchmark | Kimi K2.7 Code | Trinity Large Thinking |
|---|---|---|
| GPQA Diamond | 87.9% | — |
| SimpleQA Verified | 36.5% | — |
| Vectara Hallucination Rate | — | 6.9% |
| LMArena Expert | — | 1360 |
Multilingual Not comparable
Kimi K2.7 Code: —, Trinity Large Thinking: 46.2 (#160)
| Benchmark | Kimi K2.7 Code | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | — | 1325 |
| LMArena Chinese | — | 1373 |
| LMArena French | — | 1374 |
| LMArena German | — | 1356 |
| LMArena Japanese | — | 1311 |
| LMArena Korean | — | 1306 |
| LMArena Russian | — | 1337 |
| LMArena Spanish | — | 1357 |
Instruction Following Not comparable
Kimi K2.7 Code: —, Trinity Large Thinking: 70.5 (#162)
| Benchmark | Kimi K2.7 Code | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | — | 1334 |
Long Context Not comparable
Kimi K2.7 Code: —, Trinity Large Thinking: 41.3 (#144)
| Benchmark | Kimi K2.7 Code | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | — | 1355 |
Writing & Preference Not comparable
Kimi K2.7 Code: —, Trinity Large Thinking: 53.8 (#158)
| Benchmark | Kimi K2.7 Code | Trinity Large Thinking |
|---|---|---|
| LMArena Text | — | 1340 |
| LMArena Creative Writing | — | 1320 |
| LMArena Multi-Turn | — | 1342 |
Frequently asked questions
Is Kimi K2.7 Code better than Trinity Large Thinking?
Kimi K2.7 Code is the stronger model overall, scoring 43.3 to 38.6 on the Noometry Index. Trinity Large Thinking costs 4.4× less per token, which makes it the better buy when Kimi K2.7 Code's lead doesn't matter for your workload.
Which is cheaper, Kimi K2.7 Code or Trinity Large Thinking?
Trinity Large Thinking is cheaper. It lists at $0.25 per million input tokens and $0.80 per million output tokens; Kimi K2.7 Code lists at $0.95 and $4.
Is Kimi K2.7 Code or Trinity Large Thinking better for coding?
Kimi K2.7 Code scores higher on coding benchmarks: 42.9 versus 34.1 in the Noometry coding category.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do Kimi K2.7 Code and Trinity Large Thinking share?
4 benchmarks have published results for both models. Kimi K2.7 Code has 19 scored results on Noometry and Trinity Large Thinking has 24.