Model comparison
Grok 4.1 Fast vs Kimi K2.5
Kimi K2.5 is the stronger model overall, scoring 48.1 to 41.4 on the Noometry Index. Grok 4.1 Fast costs 3.3× less per token, which makes it the better buy when Kimi K2.5's lead doesn't matter for your workload.
Last verified . 26 shared benchmarks.
Summary
- They share 26 benchmarks with published results for both. Grok 4.1 Fast scores higher in 2 categories and Kimi K2.5 in 8 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Kimi K2.5 leads 53.6 to 33.1.
- The biggest single-benchmark swing is NYT Connections (extended): 87.4% for Grok 4.1 Fast and 69.9% for Kimi K2.5.
- Grok 4.1 Fast is cheaper at $0.20 / $0.50 per million input/output tokens, against $0.45 / $2.25 for Kimi K2.5.
- Kimi K2.5 accepts more context: 262K tokens versus 128K.
- Kimi K2.5 has downloadable open weights; the other is API-only.
Side by side
| Grok 4.1 Fast | Kimi K2.5 | |
|---|---|---|
| Provider | xAI | Moonshot AI |
| Noometry Index | 41.4 | 48.1 |
| Released | 2025-06-27 | 2026-01-27 |
| Weights | Proprietary | Open |
| Context window | 128K | 262K |
| Max output | 30K | 262K |
| Input $ / M tokens | $0.20 | $0.45 |
| Output $ / M tokens | $0.50 | $2.25 |
| Results tracked | 32 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.5 leads
Grok 4.1 Fast: 34.1 (#245), Kimi K2.5: 48.8 (#53)
| Benchmark | Grok 4.1 Fast | Kimi K2.5 |
|---|---|---|
| LMArena WebDev | 1242 | 1437 |
| LMArena Coding | 1411 | 1474 |
| ALE-Bench | 394.93 | 821.65 |
| SWE-bench Verified | — | 73.8% |
| SWE-bench Verified (bash only) | — | 70.8% |
| SWE-bench Multilingual | — | 67.3% |
| SciCode | — | 49% |
| WeirdML | — | 45.6% |
Agentic & Tool Use Grok 4.1 Fast leads
Grok 4.1 Fast: 36.3 (#39), Kimi K2.5: 34.2 (#48)
| Benchmark | Grok 4.1 Fast | Kimi K2.5 |
|---|---|---|
| Vending-Bench 2 | 1,107 | 1,198 |
| Terminal-Bench | — | 43.2% |
| Berkeley Function Calling Leaderboard | 69.6% | — |
| τ²-bench Banking | 13.1% | — |
| OSWorld | — | 63.3% |
| LMArena Search | 1171 | — |
Reasoning Grok 4.1 Fast leads
Grok 4.1 Fast: 43.4 (#49), Kimi K2.5: 31.2 (#80)
| Benchmark | Grok 4.1 Fast | Kimi K2.5 |
|---|---|---|
| SimpleBench | 56% | 46.8% |
| NYT Connections (extended) | 87.4% | 69.9% |
| LMArena Hard Prompts | 1407 | 1453 |
| ARC-AGI-2 | — | 11.8% |
| Kagi LLM Benchmark | — | 78.5% |
| ARC-AGI-1 | — | 65.3% |
| CritPt | — | 3.1% |
| Chess Puzzles | — | 12% |
| EnigmaEval | — | 3.4% |
| Thematic Generalization | — | 69.4% |
| DTBench | 87.7% | — |
| Epoch Capabilities Index | — | 148.03 |
| ForecastBench | 61 | — |
Math Kimi K2.5 leads
Grok 4.1 Fast: 31.9 (#221), Kimi K2.5: 51.8 (#53)
| Benchmark | Grok 4.1 Fast | Kimi K2.5 |
|---|---|---|
| MathArena Final-Answer Competitions | 60.9% | 62.3% |
| LMArena Math | 1408 | 1470 |
| OTIS Mock AIME 2024-2025 | — | 92.2% |
| ProofBench | 4% | — |
| FrontierMath (Feb 2025 set) | — | 27.9% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Kimi K2.5 leads
Grok 4.1 Fast: 33.1 (#207), Kimi K2.5: 53.6 (#56)
| Benchmark | Grok 4.1 Fast | Kimi K2.5 |
|---|---|---|
| Vectara Hallucination Rate | 17.8% | 14.2% |
| LMArena Expert | 1399 | 1466 |
| GPQA Diamond | — | 87.6% |
| Humanity's Last Exam | — | 24.4% |
| SimpleQA Verified | — | 34.3% |
Multimodal Kimi K2.5 leads
Grok 4.1 Fast: 37.0 (#76), Kimi K2.5: 41.1 (#39)
| Benchmark | Grok 4.1 Fast | Kimi K2.5 |
|---|---|---|
| LMArena Vision | 1201 | 1269 |
| LMArena Document | — | 1430 |
Multilingual Kimi K2.5 leads
Grok 4.1 Fast: 51.0 (#114), Kimi K2.5: 53.9 (#53)
| Benchmark | Grok 4.1 Fast | Kimi K2.5 |
|---|---|---|
| LMArena Non-English | 1391 | 1433 |
| LMArena Chinese | 1441 | 1495 |
| LMArena French | 1415 | 1454 |
| LMArena German | 1404 | 1441 |
| LMArena Japanese | 1349 | 1421 |
| LMArena Korean | 1361 | 1410 |
| LMArena Russian | 1387 | 1435 |
| LMArena Spanish | 1413 | 1450 |
Instruction Following Kimi K2.5 leads
Grok 4.1 Fast: 72.7 (#133), Kimi K2.5: 75.3 (#64)
| Benchmark | Grok 4.1 Fast | Kimi K2.5 |
|---|---|---|
| LMArena Instruction Following | 1376 | 1431 |
Long Context Kimi K2.5 leads
Grok 4.1 Fast: 42.4 (#126), Kimi K2.5: 52.1 (#7)
| Benchmark | Grok 4.1 Fast | Kimi K2.5 |
|---|---|---|
| LMArena Longer Query | 1390 | 1445 |
| Fiction.LiveBench | — | 86.1% |
| CL-bench | — | 19.3% |
| CL-bench Life | — | 13.2% |
Writing & Preference Kimi K2.5 leads
Grok 4.1 Fast: 57.2 (#131), Kimi K2.5: 65.1 (#53)
| Benchmark | Grok 4.1 Fast | Kimi K2.5 |
|---|---|---|
| LMArena Text | 1408 | 1445 |
| LMArena Creative Writing | 1394 | 1423 |
| EQ-Bench Creative Writing | 1327 | 1579 |
| LMArena Multi-Turn | 1389 | 1444 |
Frequently asked questions
Is Grok 4.1 Fast better than Kimi K2.5?
Kimi K2.5 is the stronger model overall, scoring 48.1 to 41.4 on the Noometry Index. Grok 4.1 Fast costs 3.3× less per token, which makes it the better buy when Kimi K2.5's lead doesn't matter for your workload.
Which is cheaper, Grok 4.1 Fast or Kimi K2.5?
Grok 4.1 Fast is cheaper. It lists at $0.20 per million input tokens and $0.50 per million output tokens; Kimi K2.5 lists at $0.45 and $2.25.
Is Grok 4.1 Fast or Kimi K2.5 better for coding?
Kimi K2.5 scores higher on coding benchmarks: 48.8 versus 34.1 in the Noometry coding category.
Which has the bigger context window?
Kimi K2.5 does, with 262K tokens against 128K.
How many benchmarks do Grok 4.1 Fast and Kimi K2.5 share?
26 benchmarks have published results for both models. Grok 4.1 Fast has 32 scored results on Noometry and Kimi K2.5 has 51.