Compare / head-to-head
GPT-6 Astravs
Kimi K2 Thinking
GPT-6 Astra leads 2 of 2 shared benchmarks. GPT-6 Astra has the larger context window (1.1M tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
2 – 0
GPT-6 Astra leads
Cheaper per token
—
list price, input + output
Larger context
GPT-6 Astra
1.1M tokens
Providers
2 providers
OpenAI · Moonshot AI
GPT-6 Astra
OpenAI · released 2026-09-03
textvision
Kimi K2 Thinking
Moonshot AI · released 2025-11-06
text
- Context
- 256K
- Max out
- —
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 17 · 9 core
Quality
Benchmark matrix
2 shared · 31 only GPT-6 Astra · 15 only Kimi K2 Thinking| Benchmark | GPT-6 Astra | Kimi K2 Thinking | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 2 | ||||
| SimpleBench (SimpleBench) | 86.5% ↗ | 39.6% ↗ | +46.9 pt | GPT-6 Astra |
| WeirdML (Håvard Tveit Ihle) | 93.6% ↗ | 42.8% ↗ | +50.8 pt | GPT-6 Astra |
| Only GPT-6 Astra reports · 31 | ||||
| GPQA Diamond | 96% ↗ | not reported | — | — |
| LMArena Elo | 1477.1 ↗ | not reported | — | — |
| APEX-Agents (Mercor) | 64.7% ↗ | not reported | — | — |
| AutomationBench 1.0.6 | 41.4% ↗ | not reported | — | — |
| BALROG (BALROG) | 68.3% ↗ | not reported | — | — |
| Chess Puzzles (Epoch AI run) | 72% ↗epoch run | not reported | — | — |
| DeepSWE v1.1 (Datacurve) | 74.1% ↗ | not reported | — | — |
| EBR-bench (Epoch AI run) | 76.2% ↗epoch run | not reported | — | — |
| FrontierMath Tier 4 v2 (Epoch AI run) | 97.6% ↗epoch run | not reported | — | — |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 93.7% ↗epoch run | not reported | — | — |
| FrontierSWE V2 (Proximal Labs) | 65.5% ↗ | not reported | — | — |
| Furniture Assembly (Epoch AI run) | 80% ↗epoch run | not reported | — | — |
| GSO Opt@1 (GSO) | 77.5% ↗ | not reported | — | — |
| LiveBench Agentic Coding (LiveBench) | 57.3% ↗ | not reported | — | — |
| LiveBench Coding (LiveBench) | 80.4% ↗ | not reported | — | — |
| LiveBench Data Analysis (LiveBench) | 83% ↗ | not reported | — | — |
| LiveBench Instruction Following (LiveBench) | 75.6% ↗ | not reported | — | — |
| LiveBench Language (LiveBench) | 89.4% ↗ | not reported | — | — |
| LiveBench Mathematics (LiveBench) | 96.8% ↗ | not reported | — | — |
| LiveBench Reasoning (LiveBench) | 92.7% ↗ | not reported | — | — |
| LMArena Agent (LMArena) | 0.1227 ↗ | not reported | — | — |
| LMArena Vision (LMArena) | 1284.3 ↗ | not reported | — | — |
| LMArena WebDev (LMArena) | 1787.7 ↗ | not reported | — | — |
| MirrorCode (Epoch AI run) | 46.7% ↗epoch run | not reported | — | — |
| Mystery Game Puzzles (Epoch AI run) | 84% ↗epoch run | not reported | — | — |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 100% ↗epoch run | not reported | — | — |
| SAGE (Vals AI) | 46.4% ↗ | not reported | — | — |
| SimpleQA Verified | 75.6% ↗epoch run | not reported | — | — |
| Terminal-Bench 4.0 (Vals AI) | 59.6% ↗ | not reported | — | — |
| Terminal-Bench Science 0.1 | 64.6% ↗ | not reported | — | — |
| Vending-Bench 2 (Andon Labs) | 15514.7 ↗ | not reported | — | — |
| Only Kimi K2 Thinking reports · 15 | ||||
| AIME25 (no tools) | not reported | 94.5% ↗ | — | — |
| BrowseComp (w/ tools) | not reported | 60.2% ↗ | — | — |
| BrowseComp-ZH (w/ tools) | not reported | 62.3% ↗ | — | — |
| GPQA (no tools) | not reported | 84.5% ↗ | — | — |
| HLE (Text-only) (no tools) | not reported | 23.9% ↗ | — | — |
| HLE (Text-only) (w/ tools) | not reported | 44.9% ↗ | — | — |
| HMMT25 (no tools) | not reported | 89.4% ↗ | — | — |
| IMO-AnswerBench (no tools) | not reported | 78.6% ↗ | — | — |
| LiveCodeBenchV6 (no tools) | not reported | 83.1% ↗ | — | — |
| MMLU-Pro (no tools) | not reported | 84.6% ↗ | — | — |
| Multi-SWE-bench (w/ tools) | not reported | 41.9% ↗ | — | — |
| SciCode (no tools) | not reported | 44.8% ↗ | — | — |
| SWE-bench Multilingual (w/ tools) | not reported | 61.1% ↗ | — | — |
| SWE-bench Verified (w/ tools) | not reported | 71.3% ↗ | — | — |
| Terminal-Bench (w/ simulated tools (JSON)) | not reported | 47.1% ↗ | — | — |
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-6 Astra minus Kimi K2 Thinking 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-6 Astra | Kimi K2 Thinking | Edge |
|---|---|---|---|
| Context window | 1.1M tokens | 256K tokens | GPT-6 Astra |
| Max output | 128K tokens | — | — |
| Input price / 1M | $10 ↗ | — | — |
| Output price / 1M | $50 ↗ | — | — |
| Cached input / 1M | $1 ↗ | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $60 | — | — |
| Modalities | text · vision | text | GPT-6 Astra |
| Released | 2026-09-03 | 2025-11-06 | — |
| Cited benchmark scores | 39 | 17 | — |
Reliability
Provider status
Live from /statusMore matchups
GPT-6 Astra vs …
Models sharing the most benchmarksMore matchups
Kimi K2 Thinking vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run GPT-6 Astra and Kimi K2 Thinking on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.