Compare / head-to-head
GPT-5.2vs
Kimi K2.5
GPT-5.2 leads 6 of 12 shared benchmarks. GPT-5.2 has the larger context window (400K tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
6 – 5
GPT-5.2 leads · 1 tied
Cheaper per token
—
list price, input + output
Larger context
GPT-5.2
400K tokens
Providers
2 providers
OpenAI · Moonshot AI
GPT-5.2
OpenAI · released 2025-12-11
textvision
Kimi K2.5
Moonshot AI · released 2026-01-27
textvisionvideo
- Context
- 256K
- Max out
- —
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 26 · 14 core
Quality
Benchmark matrix
12 shared · 24 only GPT-5.2 · 14 only Kimi K2.5| Benchmark | GPT-5.2 | Kimi K2.5 | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 12 | ||||
| SWE-bench Verified | 80% ↗ | 76.8% ↗ | +3.2 pt | GPT-5.2 |
| AIME 2025 | 100% ↗ | 96.1% ↗ | +3.9 pt | GPT-5.2 |
| LMArena Elo | 1412.4 ↗ | 1450.1 ↗ | -37.7 | Kimi K2.5 |
| LMArena Vision (LMArena) | 1242.8 ↗ | 1252.2 ↗ | -9.4 | Kimi K2.5 |
| LMArena WebDev (LMArena) | 1415.5 ↗ | 1435.8 ↗ | -20.3 | Kimi K2.5 |
| SAGE (Vals AI) | 49.3% ↗ | 49.9% ↗ | -0.6 pt | Kimi K2.5 |
| SimpleBench (SimpleBench) | 45.8% ↗ | 46.8% ↗ | -1 pt | Kimi K2.5 |
| SimpleQA Verified | 37.1% ↗epoch run | 34.3% ↗epoch run | +2.8 pt | GPT-5.2 |
| SWE-Bench Pro | 55.6% ↗ | 50.7% ↗ | +4.9 pt | GPT-5.2 |
| SWE-bench Verified (Epoch AI run) | 73.8% ↗epoch run | 73.8% ↗epoch run | 0 | Tie |
| Vending-Bench 2 (Andon Labs) | 3591.33 ↗ | 1198.46 ↗ | +2392.9 | GPT-5.2 |
| WeirdML (Håvard Tveit Ihle) | 72.2% ↗ | 45.6% ↗ | +26.6 pt | GPT-5.2 |
| Only GPT-5.2 reports · 24 | ||||
| GPQA Diamond | 92.4% ↗ | not reported | — | — |
| AIME 2026 | 98.3% ↗matharena | not reported | — | — |
| ARC-AGI-1 (Verified) | 86.2% ↗ | not reported | — | — |
| ARC-AGI-2 (Verified) | 52.9% ↗ | not reported | — | — |
| Chess Puzzles (Epoch AI run) | 49% ↗epoch run | not reported | — | — |
| EBR-bench (Epoch AI run) | 23% ↗epoch run | not reported | — | — |
| FrontierMath Tier 4 v2 (Epoch AI run) | 31.7% ↗epoch run | not reported | — | — |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 67.4% ↗epoch run | not reported | — | — |
| Furniture Assembly (Epoch AI run) | 38.3% ↗epoch run | not reported | — | — |
| GDPval (wins or ties) | 70.9% ↗ | not reported | — | — |
| GSO Opt@1 (GSO) | 26.5% ↗ | not reported | — | — |
| LiveBench Agentic Coding (LiveBench) | 50.3% ↗ | not reported | — | — |
| LiveBench Coding (LiveBench) | 76.1% ↗ | not reported | — | — |
| LiveBench Data Analysis (LiveBench) | 78.2% ↗ | not reported | — | — |
| LiveBench Instruction Following (LiveBench) | 61.8% ↗ | not reported | — | — |
| LiveBench Language (LiveBench) | 79.8% ↗ | not reported | — | — |
| LiveBench Mathematics (LiveBench) | 93.2% ↗ | not reported | — | — |
| LiveBench Reasoning (LiveBench) | 83.2% ↗ | not reported | — | — |
| Mystery Game Puzzles (Epoch AI run) | 23% ↗epoch run | not reported | — | — |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 96.1% ↗epoch run | not reported | — | — |
| tau2-bench Airline (Sierra) | 83% ↗ | not reported | — | — |
| tau2-bench Banking Knowledge (Sierra) | 32.2% ↗ | not reported | — | — |
| tau2-bench Retail (Sierra) | 81.6% ↗ | not reported | — | — |
| tau2-bench Telecom (Sierra) | 89.7% ↗ | not reported | — | — |
| Only Kimi K2.5 reports · 14 | ||||
| MMLU-Pro | not reported | 87.1% ↗ | — | — |
| BrowseComp | not reported | 60.6% ↗ | — | — |
| GPQA-Diamond | not reported | 87.6% ↗ | — | — |
| HLE-Full | not reported | 30.1% ↗ | — | — |
| HLE-Full (w/ tools) | not reported | 50.2% ↗ | — | — |
| HMMT 2025 (Feb) | not reported | 95.4% ↗ | — | — |
| IMO-AnswerBench | not reported | 81.8% ↗ | — | — |
| LiveCodeBench (v6) | not reported | 85% ↗ | — | — |
| MMMU-Pro | not reported | 78.5% ↗ | — | — |
| OSWorld-Verified (XLANG) | not reported | 63.3% ↗ | — | — |
| SWE-Bench Multilingual | not reported | 73% ↗ | — | — |
| Terminal Bench 2.0 | not reported | 50.8% ↗ | — | — |
| Toolathlon-Verified (HKUST) | not reported | 33% ↗ | — | — |
| VideoMMMU | not reported | 86.6% ↗ | — | — |
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 GPT-5.2 minus Kimi K2.5 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 | GPT-5.2 | Kimi K2.5 | Edge |
|---|---|---|---|
| Context window | 400K tokens | 256K tokens | GPT-5.2 |
| Max output | 128K tokens | — | — |
| Input price / 1M | $1.75 ↗ | — | — |
| Output price / 1M | $14 ↗ | — | — |
| Cached input / 1M | $0.175 ↗ | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $15.75 | — | — |
| Modalities | text · vision | text · vision · video | Kimi K2.5 |
| Released | 2025-12-11 | 2026-01-27 | — |
| Cited benchmark scores | 45 | 26 | — |
Reliability
Provider status
Live from /statusMore matchups
GPT-5.2 vs …
Models sharing the most benchmarksMore matchups
Kimi K2.5 vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run GPT-5.2 and Kimi K2.5 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.