Model comparison
Kimi K2 (Jul 2025) vs Trinity Large Thinking
Kimi K2 (Jul 2025) is the stronger model overall, scoring 41.2 to 38.6 on the Noometry Index. Trinity Large Thinking costs 2.6× less per token, which makes it the better buy when Kimi K2 (Jul 2025)'s lead doesn't matter for your workload.
Last verified . 18 shared benchmarks.
Arcee AISummary
- They share 18 benchmarks with published results for both. Kimi K2 (Jul 2025) scores higher in 6 categories and Trinity Large Thinking in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Kimi K2 (Jul 2025) leads 62.3 to 53.8.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 17.9% for Kimi K2 (Jul 2025) and 6.9% for Trinity Large Thinking.
- Trinity Large Thinking is cheaper at $0.25 / $0.80 per million input/output tokens, against $0.57 / $2.30 for Kimi K2 (Jul 2025).
Side by side
| Kimi K2 (Jul 2025) | Trinity Large Thinking | |
|---|---|---|
| Provider | Moonshot AI | Arcee AI |
| Noometry Index | 41.2 | 38.6 |
| Released | 2025-07-12 | 2026-04-01 |
| Weights | Open | Open |
| Context window | 262K | 262K |
| Max output | 262K | 80K |
| Input $ / M tokens | $0.57 | $0.25 |
| Output $ / M tokens | $2.30 | $0.80 |
| Results tracked | 42 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 42.4 (#102), Trinity Large Thinking: 34.1 (#244)
| Benchmark | Kimi K2 (Jul 2025) | Trinity Large Thinking |
|---|---|---|
| LMArena Coding | 1399 | 1381 |
| SWE-bench Verified (bash only) | 63.4% | — |
| Aider Polyglot | 59.1% | — |
| LMArena WebDev | — | 1238 |
| SciCode | — | 36.1% |
| GSO | 4.9% | — |
| WeirdML | 42.8% | — |
| ALE-Bench | 597.5 | — |
Agentic & Tool Use Not comparable
Kimi K2 (Jul 2025): 32.4 (#64), Trinity Large Thinking: —
| Benchmark | Kimi K2 (Jul 2025) | Trinity Large Thinking |
|---|---|---|
| Terminal-Bench | 35.7% | — |
| Berkeley Function Calling Leaderboard | 59.1% | — |
| METR Time Horizons | 59.2% | — |
Reasoning Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 23.3 (#179), Trinity Large Thinking: 16.9 (#298)
| Benchmark | Kimi K2 (Jul 2025) | Trinity Large Thinking |
|---|---|---|
| LMArena Hard Prompts | 1384 | 1350 |
| SimpleBench | 26.3% | — |
| Kagi LLM Benchmark | 64.4% | — |
| NYT Connections (extended) | — | 16.5% |
| CritPt | — | 0.9% |
| Thematic Generalization | — | 41.6% |
| Surface Evolver Bench | — | 15.6% |
| Epoch Capabilities Index | 146.01 | — |
| ForecastBench | 60.2 | — |
Math Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 42.7 (#83), Trinity Large Thinking: 37.6 (#149)
| Benchmark | Kimi K2 (Jul 2025) | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1397 | 1366 |
| Omni-MATH | 65.4% | — |
| FrontierMath (Feb 2025 set) | 21.4% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Trinity Large Thinking leads
Kimi K2 (Jul 2025): 37.3 (#157), Trinity Large Thinking: 40.9 (#113)
| Benchmark | Kimi K2 (Jul 2025) | Trinity Large Thinking |
|---|---|---|
| Vectara Hallucination Rate | 17.9% | 6.9% |
| LMArena Expert | 1365 | 1360 |
| MMLU-Pro | 81.9% | — |
| Confabulations | 20.4% | — |
| GPQA (HELM) | 65.3% | — |
Multilingual Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 49.6 (#130), Trinity Large Thinking: 46.2 (#160)
| Benchmark | Kimi K2 (Jul 2025) | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1372 | 1325 |
| LMArena Chinese | 1415 | 1373 |
| LMArena French | 1379 | 1374 |
| LMArena German | 1387 | 1356 |
| LMArena Japanese | 1349 | 1311 |
| LMArena Korean | 1325 | 1306 |
| LMArena Russian | 1385 | 1337 |
| LMArena Spanish | 1386 | 1357 |
Instruction Following Too close to call
Kimi K2 (Jul 2025): 71.1 (#156), Trinity Large Thinking: 70.5 (#162)
| Benchmark | Kimi K2 (Jul 2025) | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1348 | 1334 |
| IFEval | 85% | — |
Long Context Too close to call
Kimi K2 (Jul 2025): 41.2 (#145), Trinity Large Thinking: 41.3 (#144)
| Benchmark | Kimi K2 (Jul 2025) | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1353 | 1355 |
| Fiction.LiveBench | 66.7% | — |
| CL-bench | 17.6% | — |
Writing & Preference Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 62.3 (#78), Trinity Large Thinking: 53.8 (#158)
| Benchmark | Kimi K2 (Jul 2025) | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1380 | 1340 |
| LMArena Creative Writing | 1350 | 1320 |
| LMArena Multi-Turn | 1371 | 1342 |
| Short-Story Creative Writing | 85.6% | — |
| EQ-Bench Creative Writing | 1666 | — |
| WildBench | 86.2% | — |
Frequently asked questions
Is Kimi K2 (Jul 2025) better than Trinity Large Thinking?
Kimi K2 (Jul 2025) is the stronger model overall, scoring 41.2 to 38.6 on the Noometry Index. Trinity Large Thinking costs 2.6× less per token, which makes it the better buy when Kimi K2 (Jul 2025)'s lead doesn't matter for your workload.
Which is cheaper, Kimi K2 (Jul 2025) 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 (Jul 2025) lists at $0.57 and $2.30.
Is Kimi K2 (Jul 2025) or Trinity Large Thinking better for coding?
Kimi K2 (Jul 2025) scores higher on coding benchmarks: 42.4 versus 34.1 in the Noometry coding category.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do Kimi K2 (Jul 2025) and Trinity Large Thinking share?
18 benchmarks have published results for both models. Kimi K2 (Jul 2025) has 42 scored results on Noometry and Trinity Large Thinking has 24.