Model comparison
Kimi K3 vs Trinity Large Thinking
Kimi K3 is the stronger model overall, scoring 59.5 to 38.6 on the Noometry Index. Trinity Large Thinking costs 15× less per token, which makes it the better buy when Kimi K3's lead doesn't matter for your workload.
Last verified . 22 shared benchmarks.
Arcee AISummary
- They share 22 benchmarks with published results for both. Kimi K3 scores higher in 8 categories and Trinity Large Thinking in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Kimi K3 leads 63.0 to 16.9.
- The biggest single-benchmark swing is Surface Evolver Bench: 95% for Kimi K3 and 15.6% for Trinity Large Thinking.
- Trinity Large Thinking is cheaper at $0.25 / $0.80 per million input/output tokens, against $3 / $15 for Kimi K3.
- Kimi K3 accepts more context: 1.05M tokens versus 262K.
Side by side
| Kimi K3 | Trinity Large Thinking | |
|---|---|---|
| Provider | Moonshot AI | Arcee AI |
| Noometry Index | 59.5 | 38.6 |
| Released | 2026-07-16 | 2026-04-01 |
| Weights | Open | Open |
| Context window | 1.05M | 262K |
| Max output | 1.05M | 80K |
| Input $ / M tokens | $3 | $0.25 |
| Output $ / M tokens | $15 | $0.80 |
| Results tracked | 53 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K3 leads
Kimi K3: 61.0 (#10), Trinity Large Thinking: 34.1 (#244)
| Benchmark | Kimi K3 | Trinity Large Thinking |
|---|---|---|
| LMArena WebDev | 1654 | 1238 |
| SciCode | 59.5% | 36.1% |
| LMArena Coding | 1508 | 1381 |
| DeepSWE | 68.5% | — |
| FrontierCode | 44.2% | — |
| FrontierSWE | 25.9% | — |
| WeirdML | 82.6% | — |
| ALE-Bench | 1,524 | — |
Agentic & Tool Use Not comparable
Kimi K3: 41.8 (#20), Trinity Large Thinking: —
| Benchmark | Kimi K3 | Trinity Large Thinking |
|---|---|---|
| APEX-Agents | 50.6% | — |
| τ²-bench Banking | 37.1% | — |
| PostTrainBench | 32% | — |
| GBAEval | 48.3% | — |
| GDP.pdf | 19% | — |
| Vending-Bench 2 | 5,165 | — |
Reasoning Kimi K3 leads
Kimi K3: 63.0 (#17), Trinity Large Thinking: 16.9 (#298)
| Benchmark | Kimi K3 | Trinity Large Thinking |
|---|---|---|
| NYT Connections (extended) | 93.6% | 16.5% |
| CritPt | 23.4% | 0.9% |
| LMArena Hard Prompts | 1496 | 1350 |
| Surface Evolver Bench | 95% | 15.6% |
| ARC-AGI-2 | 60.4% | — |
| SimpleBench | 60.7% | — |
| ARC-AGI-1 | 94.5% | — |
| Chess Puzzles | 39% | — |
| Thematic Generalization | — | 41.6% |
| Mystery Game Puzzles | 26% | — |
| DTBench | 91.2% | — |
| LMCA | 52.7% | — |
| Epoch Capabilities Index | 157.45 | — |
| ForecastBench | 61.1 | — |
Math Kimi K3 leads
Kimi K3: 74.2 (#16), Trinity Large Thinking: 37.6 (#149)
| Benchmark | Kimi K3 | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1491 | 1366 |
| FrontierMath (Tiers 1-3) | 72.2% | — |
| FrontierMath Tier 4 | 39% | — |
| MathArena Final-Answer Competitions | 87.8% | — |
| OTIS Mock AIME 2024-2025 | 97.2% | — |
| ProofBench | 87% | — |
Knowledge Kimi K3 leads
Kimi K3: 63.2 (#21), Trinity Large Thinking: 40.9 (#113)
| Benchmark | Kimi K3 | Trinity Large Thinking |
|---|---|---|
| LMArena Expert | 1521 | 1360 |
| GPQA Diamond | 93.1% | — |
| SimpleQA Verified | 50.6% | — |
| Vectara Hallucination Rate | — | 6.9% |
Multimodal Not comparable
Kimi K3: 37.8 (#70), Trinity Large Thinking: —
| Benchmark | Kimi K3 | Trinity Large Thinking |
|---|---|---|
| Blueprint-Bench 2 | 29.5% | — |
| Furniture Assembly | 34.2% | — |
Multilingual Kimi K3 leads
Kimi K3: 56.3 (#21), Trinity Large Thinking: 46.2 (#160)
| Benchmark | Kimi K3 | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1466 | 1325 |
| LMArena Chinese | 1529 | 1373 |
| LMArena French | 1491 | 1374 |
| LMArena German | 1488 | 1356 |
| LMArena Japanese | 1487 | 1311 |
| LMArena Korean | 1458 | 1306 |
| LMArena Russian | 1482 | 1337 |
| LMArena Spanish | 1472 | 1357 |
Instruction Following Kimi K3 leads
Kimi K3: 77.7 (#14), Trinity Large Thinking: 70.5 (#162)
| Benchmark | Kimi K3 | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1483 | 1334 |
Long Context Kimi K3 leads
Kimi K3: 45.8 (#29), Trinity Large Thinking: 41.3 (#144)
| Benchmark | Kimi K3 | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1494 | 1355 |
Writing & Preference Kimi K3 leads
Kimi K3: 76.6 (#4), Trinity Large Thinking: 53.8 (#158)
| Benchmark | Kimi K3 | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1476 | 1340 |
| LMArena Creative Writing | 1454 | 1320 |
| LMArena Multi-Turn | 1488 | 1342 |
| EQ-Bench Creative Writing | 2082 | — |
| EQ-Bench 4 | 1339 | — |
Frequently asked questions
Is Kimi K3 better than Trinity Large Thinking?
Kimi K3 is the stronger model overall, scoring 59.5 to 38.6 on the Noometry Index. Trinity Large Thinking costs 15× less per token, which makes it the better buy when Kimi K3's lead doesn't matter for your workload.
Which is cheaper, Kimi K3 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 K3 lists at $3 and $15.
Is Kimi K3 or Trinity Large Thinking better for coding?
Kimi K3 scores higher on coding benchmarks: 61.0 versus 34.1 in the Noometry coding category.
Which has the bigger context window?
Kimi K3 does, with 1.05M tokens against 262K.
How many benchmarks do Kimi K3 and Trinity Large Thinking share?
22 benchmarks have published results for both models. Kimi K3 has 53 scored results on Noometry and Trinity Large Thinking has 24.