Model comparison
Grok Build 0.1 vs Kimi K2 (Jul 2025)
Kimi K2 (Jul 2025) is the stronger model overall, scoring 41.2 to 36.4 on the Noometry Index.
Last verified . 0 shared benchmarks.
Summary
- The widest gap is in agentic & tool use, where Kimi K2 (Jul 2025) leads 32.4 to 22.7.
- Kimi K2 (Jul 2025) is cheaper at $0.57 / $2.30 per million input/output tokens, against $1 / $2 for Grok Build 0.1.
- Kimi K2 (Jul 2025) accepts more context: 262K tokens versus 256K.
- Kimi K2 (Jul 2025) has downloadable open weights; the other is API-only.
Side by side
| Grok Build 0.1 | Kimi K2 (Jul 2025) | |
|---|---|---|
| Provider | xAI | Moonshot AI |
| Noometry Index | 36.4 | 41.2 |
| Released | 2026-04-16 | 2025-07-12 |
| Weights | Proprietary | Open |
| Context window | 256K | 262K |
| Max output | 256K | 262K |
| Input $ / M tokens | $1 | $0.57 |
| Output $ / M tokens | $2 | $2.30 |
| Results tracked | 3 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Grok Build 0.1: 43.1 (#91), Kimi K2 (Jul 2025): 42.4 (#102)
| Benchmark | Grok Build 0.1 | Kimi K2 (Jul 2025) |
|---|---|---|
| SWE-bench Verified (bash only) | — | 63.4% |
| Aider Polyglot | — | 59.1% |
| SciCode | 50.2% | — |
| GSO | — | 4.9% |
| WeirdML | — | 42.8% |
| LMArena Coding | — | 1399 |
| ALE-Bench | — | 597.5 |
Agentic & Tool Use Kimi K2 (Jul 2025) leads
Grok Build 0.1: 22.7 (#129), Kimi K2 (Jul 2025): 32.4 (#64)
| Benchmark | Grok Build 0.1 | Kimi K2 (Jul 2025) |
|---|---|---|
| Terminal-Bench | — | 35.7% |
| Berkeley Function Calling Leaderboard | — | 59.1% |
| GBAEval | 2.4% | — |
| METR Time Horizons | — | 59.2% |
Reasoning Grok Build 0.1 leads
Grok Build 0.1: 32.2 (#77), Kimi K2 (Jul 2025): 23.3 (#179)
| Benchmark | Grok Build 0.1 | Kimi K2 (Jul 2025) |
|---|---|---|
| SimpleBench | — | 26.3% |
| Kagi LLM Benchmark | — | 64.4% |
| CritPt | 9.1% | — |
| LMArena Hard Prompts | — | 1384 |
| Epoch Capabilities Index | — | 146.01 |
| ForecastBench | — | 60.2 |
Math Not comparable
Grok Build 0.1: —, Kimi K2 (Jul 2025): 42.7 (#83)
| Benchmark | Grok Build 0.1 | Kimi K2 (Jul 2025) |
|---|---|---|
| Omni-MATH | — | 65.4% |
| LMArena Math | — | 1397 |
| FrontierMath (Feb 2025 set) | — | 21.4% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Not comparable
Grok Build 0.1: —, Kimi K2 (Jul 2025): 37.3 (#157)
| Benchmark | Grok Build 0.1 | Kimi K2 (Jul 2025) |
|---|---|---|
| MMLU-Pro | — | 81.9% |
| Confabulations | — | 20.4% |
| Vectara Hallucination Rate | — | 17.9% |
| GPQA (HELM) | — | 65.3% |
| LMArena Expert | — | 1365 |
Multilingual Not comparable
Grok Build 0.1: —, Kimi K2 (Jul 2025): 49.6 (#130)
| Benchmark | Grok Build 0.1 | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Non-English | — | 1372 |
| LMArena Chinese | — | 1415 |
| LMArena French | — | 1379 |
| LMArena German | — | 1387 |
| LMArena Japanese | — | 1349 |
| LMArena Korean | — | 1325 |
| LMArena Russian | — | 1385 |
| LMArena Spanish | — | 1386 |
Instruction Following Not comparable
Grok Build 0.1: —, Kimi K2 (Jul 2025): 71.1 (#156)
| Benchmark | Grok Build 0.1 | Kimi K2 (Jul 2025) |
|---|---|---|
| IFEval | — | 85% |
| LMArena Instruction Following | — | 1348 |
Long Context Not comparable
Grok Build 0.1: —, Kimi K2 (Jul 2025): 41.2 (#145)
| Benchmark | Grok Build 0.1 | Kimi K2 (Jul 2025) |
|---|---|---|
| Fiction.LiveBench | — | 66.7% |
| CL-bench | — | 17.6% |
| LMArena Longer Query | — | 1353 |
Writing & Preference Not comparable
Grok Build 0.1: —, Kimi K2 (Jul 2025): 62.3 (#78)
| Benchmark | Grok Build 0.1 | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Text | — | 1380 |
| LMArena Creative Writing | — | 1350 |
| Short-Story Creative Writing | — | 85.6% |
| EQ-Bench Creative Writing | — | 1666 |
| WildBench | — | 86.2% |
| LMArena Multi-Turn | — | 1371 |
Frequently asked questions
Is Grok Build 0.1 better than Kimi K2 (Jul 2025)?
Kimi K2 (Jul 2025) is the stronger model overall, scoring 41.2 to 36.4 on the Noometry Index.
Which is cheaper, Grok Build 0.1 or Kimi K2 (Jul 2025)?
Kimi K2 (Jul 2025) is cheaper. It lists at $0.57 per million input tokens and $2.30 per million output tokens; Grok Build 0.1 lists at $1 and $2.
Is Grok Build 0.1 or Kimi K2 (Jul 2025) better for coding?
They score almost the same on coding (43.1 vs 42.4); test both on your own repository before choosing.
Which has the bigger context window?
Kimi K2 (Jul 2025) does, with 262K tokens against 256K.
How many benchmarks do Grok Build 0.1 and Kimi K2 (Jul 2025) share?
0 benchmarks have published results for both models. Grok Build 0.1 has 3 scored results on Noometry and Kimi K2 (Jul 2025) has 42.