Compare / head-to-head
Kimi K2.7 CodevsPhi-4 Reasoning
Kimi K2.7 Code leads 1 of 1 shared benchmark. Kimi K2.7 Code has the larger context window (256K tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
1 – 0
Kimi K2.7 Code leads
Cheaper per token
—
list price, input + output
Larger context
Kimi K2.7 Code
256K tokens
Provider uptime (30d)
100% · —
Moonshot AI · Microsoft
Kimi K2.7 Code
Moonshot AI · released 2026-06-12
textvision
- Context
- 256K
- Max out
- —
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 11 · 5 core
Phi-4 Reasoning
Microsoft · released 2025-04-30
text
- Context
- 33K
- Max out
- 33K
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 4 · 4 core
Quality
Benchmark matrix
1 shared · 10 only Kimi K2.7 Code · 3 only Phi-4 Reasoning| Benchmark | Kimi K2.7 Code | Phi-4 Reasoning | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 1 | ||||
| GPQA Diamond | 87.9% ↗epoch | 65.8% ↗ | +22.1 pt | Kimi K2.7 Code |
| Only Kimi K2.7 Code reports · 10 | ||||
| FrontierMath Tier 4 v2 (Epoch AI run) | 12.2% ↗epoch | not reported | — | — |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 54% ↗epoch | not reported | — | — |
| Kimi Claw 24/7 Bench | 46.9% ↗ | not reported | — | — |
| Kimi Code Bench v2 | 62% ↗ | not reported | — | — |
| MCP-Atlas | 76% ↗ | not reported | — | — |
| MCPMark-Verified | 81.1% ↗ | not reported | — | — |
| MLS-Bench-Lite | 35.1% ↗ | not reported | — | — |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 95.6% ↗epoch | not reported | — | — |
| ProgramBench | 53.6% ↗ | not reported | — | — |
| SimpleQA Verified | 36.5% ↗epoch | not reported | — | — |
| Only Phi-4 Reasoning reports · 3 | ||||
| MMLU-Pro | not reported | 74.3% ↗ | — | — |
| AIME 2025 | not reported | 62.9% ↗ | — | — |
| HumanEval+ | not reported | 92.9% ↗ | — | — |
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is Kimi K2.7 Code minus Phi-4 Reasoning in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing
Side by side
Official pricing pages and model cards| Spec | Kimi K2.7 Code | Phi-4 Reasoning | Edge |
|---|---|---|---|
| Context window | 256K tokens | 33K tokens | Kimi K2.7 Code |
| Max output | — | 33K tokens | — |
| Input price / 1M | — | — | — |
| Output price / 1M | — | — | — |
| Cached input / 1M | — | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | — | — | — |
| Modalities | text · vision | text | Kimi K2.7 Code |
| Released | 2026-06-12 | 2025-04-30 | — |
| Cited benchmark scores | 11 | 4 | — |
Reliability
Provider status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
Kimi K2.7 Code vs …
Models sharing the most benchmarksMore matchups
Phi-4 Reasoning vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Kimi K2.7 Code and Phi-4 Reasoning on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.