Model comparison
Kimi K2.7 Code vs Sonar
Kimi K2.7 Code is the stronger model overall, scoring 43.3 to 38.5 on the Noometry Index. Sonar costs 1.7× less per token, which makes it the better buy when Kimi K2.7 Code's lead doesn't matter for your workload.
Last verified . 0 shared benchmarks.
PerplexitySummary
- The widest gap is in math, where Kimi K2.7 Code leads 52.9 to 33.7.
- Sonar is cheaper at $1 / $1 per million input/output tokens, against $0.95 / $4 for Kimi K2.7 Code.
- Kimi K2.7 Code accepts more context: 262K tokens versus 128K.
- Kimi K2.7 Code has downloadable open weights; the other is API-only.
Side by side
| Kimi K2.7 Code | Sonar | |
|---|---|---|
| Provider | Moonshot AI | Perplexity |
| Noometry Index | 43.3 | 38.5 |
| Released | 2026-06-12 | 2024-01-01 |
| Weights | Open | Proprietary |
| Context window | 262K | 128K |
| Max output | 262K | 4K |
| Input $ / M tokens | $0.95 | $1 |
| Output $ / M tokens | $4 | $1 |
| Results tracked | 19 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.7 Code leads
Kimi K2.7 Code: 42.9 (#95), Sonar: 35.7 (#221)
| Benchmark | Kimi K2.7 Code | Sonar |
|---|---|---|
| DeepSWE | 30.5% | — |
| FrontierCode | 30.1% | — |
| LMArena WebDev | 1473 | — |
| SciCode | 47.5% | — |
| WeirdML | 54.1% | — |
| LiveBench Coding | — | 35.1% |
| ALE-Bench | 886.23 | — |
Agentic & Tool Use Not comparable
Kimi K2.7 Code: 24.0 (#122), Sonar: —
| Benchmark | Kimi K2.7 Code | Sonar |
|---|---|---|
| APEX-Agents | 37.6% | — |
| GBAEval | 0.9% | — |
| Vending-Bench 2 | 5,083 | — |
Reasoning Kimi K2.7 Code leads
Kimi K2.7 Code: 39.0 (#61), Sonar: 21.1 (#227)
| Benchmark | Kimi K2.7 Code | Sonar |
|---|---|---|
| SimpleBench | 57.9% | — |
| CritPt | 10% | — |
| Chess Puzzles | 21% | — |
| LiveBench Reasoning | — | 46.3% |
| LiveBench Data Analysis | — | 37.9% |
| Surface Evolver Bench | 48.8% | — |
| Epoch Capabilities Index | 149.97 | — |
| LiveBench | — | 46.9% |
Math Kimi K2.7 Code leads
Kimi K2.7 Code: 52.9 (#48), Sonar: 33.7 (#200)
| Benchmark | Kimi K2.7 Code | Sonar |
|---|---|---|
| FrontierMath (Tiers 1-3) | 54% | — |
| FrontierMath Tier 4 | 12.2% | — |
| OTIS Mock AIME 2024-2025 | 95.6% | — |
| LiveBench Math | — | 41.6% |
Knowledge Not comparable
Kimi K2.7 Code: 53.5 (#57), Sonar: —
| Benchmark | Kimi K2.7 Code | Sonar |
|---|---|---|
| GPQA Diamond | 87.9% | — |
| SimpleQA Verified | 36.5% | — |
Instruction Following Not comparable
Kimi K2.7 Code: —, Sonar: 71.4 (#150)
| Benchmark | Kimi K2.7 Code | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
Writing & Preference Not comparable
Kimi K2.7 Code: —, Sonar: 52.6 (#167)
| Benchmark | Kimi K2.7 Code | Sonar |
|---|---|---|
| LiveBench Language | — | 44.1% |
Frequently asked questions
Is Kimi K2.7 Code better than Sonar?
Kimi K2.7 Code is the stronger model overall, scoring 43.3 to 38.5 on the Noometry Index. Sonar costs 1.7× less per token, which makes it the better buy when Kimi K2.7 Code's lead doesn't matter for your workload.
Which is cheaper, Kimi K2.7 Code or Sonar?
Sonar is cheaper. It lists at $1 per million input tokens and $1 per million output tokens; Kimi K2.7 Code lists at $0.95 and $4.
Is Kimi K2.7 Code or Sonar better for coding?
Kimi K2.7 Code scores higher on coding benchmarks: 42.9 versus 35.7 in the Noometry coding category.
Which has the bigger context window?
Kimi K2.7 Code does, with 262K tokens against 128K.
How many benchmarks do Kimi K2.7 Code and Sonar share?
0 benchmarks have published results for both models. Kimi K2.7 Code has 19 scored results on Noometry and Sonar has 7.