Compare / head-to-head
GPT-5.2vs
Kimi K2-0905
GPT-5.2 leads 2 of 2 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
2 – 0
GPT-5.2 leads
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 K2-0905
Moonshot AI · released 2025-09-05
text
- Context
- 256K
- Max out
- —
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 6 · 3 core
Quality
Benchmark matrix
2 shared · 34 only GPT-5.2 · 4 only Kimi K2-0905| Benchmark | GPT-5.2 | Kimi K2-0905 | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 2 | ||||
| SWE-bench Verified | 80% ↗ | 69.2% ↗ | +10.8 pt | GPT-5.2 |
| WeirdML (Håvard Tveit Ihle) | 72.2% ↗ | 36.7% ↗ | +35.5 pt | GPT-5.2 |
| Only GPT-5.2 reports · 34 | ||||
| GPQA Diamond | 92.4% ↗ | not reported | — | — |
| AIME 2025 | 100% ↗ | not reported | — | — |
| AIME 2026 | 98.3% ↗matharena | not reported | — | — |
| LMArena Elo | 1412.4 ↗ | 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 | — | — |
| LMArena Vision (LMArena) | 1242.8 ↗ | not reported | — | — |
| LMArena WebDev (LMArena) | 1415.5 ↗ | 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 | — | — |
| SAGE (Vals AI) | 49.3% ↗ | not reported | — | — |
| SimpleBench (SimpleBench) | 45.8% ↗ | not reported | — | — |
| SimpleQA Verified | 37.1% ↗epoch run | not reported | — | — |
| SWE-Bench Pro | 55.6% ↗ | not reported | — | — |
| SWE-bench Verified (Epoch AI run) | 73.8% ↗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 | — | — |
| Vending-Bench 2 (Andon Labs) | 3591.33 ↗ | not reported | — | — |
| Only Kimi K2-0905 reports · 4 | ||||
| Multi-SWE-Bench | not reported | 33.5% ↗ | — | — |
| SWE-Bench Multilingual | not reported | 55.9% ↗ | — | — |
| SWE-Dev | not reported | 66.6% ↗ | — | — |
| Terminal-Bench (Terminus-2) | not reported | 44.5% ↗ | — | — |
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 K2-0905 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 K2-0905 | 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 | GPT-5.2 |
| Released | 2025-12-11 | 2025-09-05 | — |
| Cited benchmark scores | 45 | 6 | — |
Reliability
Provider status
Live from /statusMore matchups
GPT-5.2 vs …
Models sharing the most benchmarksMore matchups
Kimi K2-0905 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 K2-0905 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.