Model comparison
Kimi K2 (Jul 2025) vs Nemotron 3 Ultra
Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 41.2 on the Noometry Index.
Last verified . 19 shared benchmarks.
NVIDIASummary
- They share 19 benchmarks with published results for both. Kimi K2 (Jul 2025) scores higher in 3 categories and Nemotron 3 Ultra in 6 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Nemotron 3 Ultra leads 52.5 to 37.3.
- Nemotron 3 Ultra is cheaper at $0.50 / $2.20 per million input/output tokens, against $0.57 / $2.30 for Kimi K2 (Jul 2025).
Side by side
| Kimi K2 (Jul 2025) | Nemotron 3 Ultra | |
|---|---|---|
| Provider | Moonshot AI | NVIDIA |
| Noometry Index | 41.2 | 42.5 |
| Released | 2025-07-12 | 2026-06-04 |
| Weights | Open | Open |
| Context window | 262K | 262K |
| Max output | 262K | 128K |
| Input $ / M tokens | $0.57 | $0.50 |
| Output $ / M tokens | $2.30 | $2.20 |
| Results tracked | 42 | 30 |
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), Nemotron 3 Ultra: 38.1 (#182)
| Benchmark | Kimi K2 (Jul 2025) | Nemotron 3 Ultra |
|---|---|---|
| WeirdML | 42.8% | 43.5% |
| LMArena Coding | 1399 | 1468 |
| FrontierCode | — | 13.6% |
| SWE-bench Verified (bash only) | 63.4% | — |
| Aider Polyglot | 59.1% | — |
| SciCode | — | 40.3% |
| GSO | 4.9% | — |
| ALE-Bench | 597.5 | — |
Agentic & Tool Use Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 32.4 (#64), Nemotron 3 Ultra: 23.4 (#126)
| Benchmark | Kimi K2 (Jul 2025) | Nemotron 3 Ultra |
|---|---|---|
| Terminal-Bench | 35.7% | — |
| APEX-Agents | — | 22.7% |
| Berkeley Function Calling Leaderboard | 59.1% | — |
| METR Time Horizons | 59.2% | — |
Reasoning Nemotron 3 Ultra leads
Kimi K2 (Jul 2025): 23.3 (#179), Nemotron 3 Ultra: 31.0 (#82)
| Benchmark | Kimi K2 (Jul 2025) | Nemotron 3 Ultra |
|---|---|---|
| LMArena Hard Prompts | 1384 | 1452 |
| Epoch Capabilities Index | 146.01 | 146.17 |
| SimpleBench | 26.3% | — |
| Kagi LLM Benchmark | 64.4% | — |
| CritPt | — | 3.1% |
| Chess Puzzles | — | 12% |
| Mystery Game Puzzles | — | 20% |
| DTBench | — | 90.1% |
| LMCA | — | 36.9% |
| ForecastBench | 60.2 | — |
Math Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 42.7 (#83), Nemotron 3 Ultra: 35.3 (#187)
| Benchmark | Kimi K2 (Jul 2025) | Nemotron 3 Ultra |
|---|---|---|
| LMArena Math | 1397 | 1457 |
| OTIS Mock AIME 2024-2025 | — | 86.7% |
| ProofBench | — | 2% |
| Omni-MATH | 65.4% | — |
| FrontierMath (Feb 2025 set) | 21.4% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Nemotron 3 Ultra leads
Kimi K2 (Jul 2025): 37.3 (#157), Nemotron 3 Ultra: 52.5 (#61)
| Benchmark | Kimi K2 (Jul 2025) | Nemotron 3 Ultra |
|---|---|---|
| LMArena Expert | 1365 | 1472 |
| GPQA Diamond | — | 85.4% |
| MMLU-Pro | 81.9% | — |
| Confabulations | 20.4% | — |
| Vectara Hallucination Rate | 17.9% | — |
| GPQA (HELM) | 65.3% | — |
Multilingual Nemotron 3 Ultra leads
Kimi K2 (Jul 2025): 49.6 (#130), Nemotron 3 Ultra: 53.5 (#64)
| Benchmark | Kimi K2 (Jul 2025) | Nemotron 3 Ultra |
|---|---|---|
| LMArena Non-English | 1372 | 1427 |
| LMArena Chinese | 1415 | 1497 |
| LMArena French | 1379 | 1472 |
| LMArena German | 1387 | 1471 |
| LMArena Korean | 1325 | 1386 |
| LMArena Russian | 1385 | 1417 |
| LMArena Spanish | 1386 | 1454 |
| LMArena Japanese | 1349 | — |
Instruction Following Nemotron 3 Ultra leads
Kimi K2 (Jul 2025): 71.1 (#156), Nemotron 3 Ultra: 74.7 (#88)
| Benchmark | Kimi K2 (Jul 2025) | Nemotron 3 Ultra |
|---|---|---|
| LMArena Instruction Following | 1348 | 1418 |
| IFEval | 85% | — |
Long Context Nemotron 3 Ultra leads
Kimi K2 (Jul 2025): 41.2 (#145), Nemotron 3 Ultra: 43.9 (#81)
| Benchmark | Kimi K2 (Jul 2025) | Nemotron 3 Ultra |
|---|---|---|
| LMArena Longer Query | 1353 | 1437 |
| Fiction.LiveBench | 66.7% | — |
| CL-bench | 17.6% | — |
Writing & Preference Nemotron 3 Ultra leads
Kimi K2 (Jul 2025): 62.3 (#78), Nemotron 3 Ultra: 66.3 (#36)
| Benchmark | Kimi K2 (Jul 2025) | Nemotron 3 Ultra |
|---|---|---|
| LMArena Text | 1380 | 1445 |
| LMArena Creative Writing | 1350 | 1398 |
| EQ-Bench Creative Writing | 1666 | 1692 |
| LMArena Multi-Turn | 1371 | 1411 |
| Short-Story Creative Writing | 85.6% | — |
| WildBench | 86.2% | — |
Frequently asked questions
Is Kimi K2 (Jul 2025) better than Nemotron 3 Ultra?
Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 41.2 on the Noometry Index.
Which is cheaper, Kimi K2 (Jul 2025) or Nemotron 3 Ultra?
Nemotron 3 Ultra is cheaper. It lists at $0.50 per million input tokens and $2.20 per million output tokens; Kimi K2 (Jul 2025) lists at $0.57 and $2.30.
Is Kimi K2 (Jul 2025) or Nemotron 3 Ultra better for coding?
Kimi K2 (Jul 2025) scores higher on coding benchmarks: 42.4 versus 38.1 in the Noometry coding category.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do Kimi K2 (Jul 2025) and Nemotron 3 Ultra share?
19 benchmarks have published results for both models. Kimi K2 (Jul 2025) has 42 scored results on Noometry and Nemotron 3 Ultra has 30.