Model comparison
Grok 4.1 Fast vs Kimi K3
Kimi K3 is the stronger model overall, scoring 59.5 to 41.4 on the Noometry Index. Grok 4.1 Fast costs 22× less per token, which makes it the better buy when Kimi K3's lead doesn't matter for your workload.
Last verified . 28 shared benchmarks.
Summary
- They share 28 benchmarks with published results for both. Grok 4.1 Fast scores higher in 0 categories and Kimi K3 in 10 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K3 leads 74.2 to 31.9.
- The biggest single-benchmark swing is ProofBench: 4% for Grok 4.1 Fast and 87% for Kimi K3.
- Grok 4.1 Fast is cheaper at $0.20 / $0.50 per million input/output tokens, against $3 / $15 for Kimi K3.
- Kimi K3 accepts more context: 1.05M tokens versus 128K.
- Kimi K3 has downloadable open weights; the other is API-only.
Side by side
| Grok 4.1 Fast | Kimi K3 | |
|---|---|---|
| Provider | xAI | Moonshot AI |
| Noometry Index | 41.4 | 59.5 |
| Released | 2025-06-27 | 2026-07-16 |
| Weights | Proprietary | Open |
| Context window | 128K | 1.05M |
| Max output | 30K | 1.05M |
| Input $ / M tokens | $0.20 | $3 |
| Output $ / M tokens | $0.50 | $15 |
| Results tracked | 32 | 53 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K3 leads
Grok 4.1 Fast: 34.1 (#245), Kimi K3: 61.0 (#10)
| Benchmark | Grok 4.1 Fast | Kimi K3 |
|---|---|---|
| LMArena WebDev | 1242 | 1654 |
| LMArena Coding | 1411 | 1508 |
| ALE-Bench | 394.93 | 1,524 |
| DeepSWE | — | 68.5% |
| FrontierCode | — | 44.2% |
| FrontierSWE | — | 25.9% |
| SciCode | — | 59.5% |
| WeirdML | — | 82.6% |
Agentic & Tool Use Kimi K3 leads
Grok 4.1 Fast: 36.3 (#39), Kimi K3: 41.8 (#20)
| Benchmark | Grok 4.1 Fast | Kimi K3 |
|---|---|---|
| τ²-bench Banking | 13.1% | 37.1% |
| Vending-Bench 2 | 1,107 | 5,165 |
| APEX-Agents | — | 50.6% |
| Berkeley Function Calling Leaderboard | 69.6% | — |
| PostTrainBench | — | 32% |
| GBAEval | — | 48.3% |
| GDP.pdf | — | 19% |
| LMArena Search | 1171 | — |
Reasoning Kimi K3 leads
Grok 4.1 Fast: 43.4 (#49), Kimi K3: 63.0 (#17)
| Benchmark | Grok 4.1 Fast | Kimi K3 |
|---|---|---|
| SimpleBench | 56% | 60.7% |
| NYT Connections (extended) | 87.4% | 93.6% |
| LMArena Hard Prompts | 1407 | 1496 |
| DTBench | 87.7% | 91.2% |
| ForecastBench | 61 | 61.1 |
| ARC-AGI-2 | — | 60.4% |
| ARC-AGI-1 | — | 94.5% |
| CritPt | — | 23.4% |
| Chess Puzzles | — | 39% |
| Mystery Game Puzzles | — | 26% |
| LMCA | — | 52.7% |
| Surface Evolver Bench | — | 95% |
| Epoch Capabilities Index | — | 157.45 |
Math Kimi K3 leads
Grok 4.1 Fast: 31.9 (#221), Kimi K3: 74.2 (#16)
| Benchmark | Grok 4.1 Fast | Kimi K3 |
|---|---|---|
| MathArena Final-Answer Competitions | 60.9% | 87.8% |
| ProofBench | 4% | 87% |
| LMArena Math | 1408 | 1491 |
| FrontierMath (Tiers 1-3) | — | 72.2% |
| FrontierMath Tier 4 | — | 39% |
| OTIS Mock AIME 2024-2025 | — | 97.2% |
Knowledge Kimi K3 leads
Grok 4.1 Fast: 33.1 (#207), Kimi K3: 63.2 (#21)
| Benchmark | Grok 4.1 Fast | Kimi K3 |
|---|---|---|
| LMArena Expert | 1399 | 1521 |
| GPQA Diamond | — | 93.1% |
| SimpleQA Verified | — | 50.6% |
| Vectara Hallucination Rate | 17.8% | — |
Multimodal Too close to call
Grok 4.1 Fast: 37.0 (#76), Kimi K3: 37.8 (#70)
| Benchmark | Grok 4.1 Fast | Kimi K3 |
|---|---|---|
| LMArena Vision | 1201 | — |
| Blueprint-Bench 2 | — | 29.5% |
| Furniture Assembly | — | 34.2% |
Multilingual Kimi K3 leads
Grok 4.1 Fast: 51.0 (#114), Kimi K3: 56.3 (#21)
| Benchmark | Grok 4.1 Fast | Kimi K3 |
|---|---|---|
| LMArena Non-English | 1391 | 1466 |
| LMArena Chinese | 1441 | 1529 |
| LMArena French | 1415 | 1491 |
| LMArena German | 1404 | 1488 |
| LMArena Japanese | 1349 | 1487 |
| LMArena Korean | 1361 | 1458 |
| LMArena Russian | 1387 | 1482 |
| LMArena Spanish | 1413 | 1472 |
Instruction Following Kimi K3 leads
Grok 4.1 Fast: 72.7 (#133), Kimi K3: 77.7 (#14)
| Benchmark | Grok 4.1 Fast | Kimi K3 |
|---|---|---|
| LMArena Instruction Following | 1376 | 1483 |
Long Context Kimi K3 leads
Grok 4.1 Fast: 42.4 (#126), Kimi K3: 45.8 (#29)
| Benchmark | Grok 4.1 Fast | Kimi K3 |
|---|---|---|
| LMArena Longer Query | 1390 | 1494 |
Writing & Preference Kimi K3 leads
Grok 4.1 Fast: 57.2 (#131), Kimi K3: 76.6 (#4)
| Benchmark | Grok 4.1 Fast | Kimi K3 |
|---|---|---|
| LMArena Text | 1408 | 1476 |
| LMArena Creative Writing | 1394 | 1454 |
| EQ-Bench Creative Writing | 1327 | 2082 |
| LMArena Multi-Turn | 1389 | 1488 |
| EQ-Bench 4 | — | 1339 |
Frequently asked questions
Is Grok 4.1 Fast better than Kimi K3?
Kimi K3 is the stronger model overall, scoring 59.5 to 41.4 on the Noometry Index. Grok 4.1 Fast costs 22× less per token, which makes it the better buy when Kimi K3's lead doesn't matter for your workload.
Which is cheaper, Grok 4.1 Fast or Kimi K3?
Grok 4.1 Fast is cheaper. It lists at $0.20 per million input tokens and $0.50 per million output tokens; Kimi K3 lists at $3 and $15.
Is Grok 4.1 Fast or Kimi K3 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 128K.
How many benchmarks do Grok 4.1 Fast and Kimi K3 share?
28 benchmarks have published results for both models. Grok 4.1 Fast has 32 scored results on Noometry and Kimi K3 has 53.