Compare / head-to-head
Kimi K2vs
Solar Pro 3
Kimi K2 leads 1 of 1 shared benchmark. Both offer a 128K-token context window.
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
1 – 0
Kimi K2 leads
Cheaper per token
—
list price, input + output
Larger context
Tie
both 128K tokens
Providers
2 providers
Moonshot AI · Upstage
Kimi K2
Moonshot AI · released 2025-07-11
text
- Context
- 128K
- Max out
- —
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 18 · 7 core
Solar Pro 3
Upstage · released 2026-01-26
text
Quality
Benchmark matrix
1 shared · 17 only Kimi K2 · 11 only Solar Pro 3| Benchmark | Kimi K2 | Solar Pro 3 | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 1 | ||||
| GPQA-Diamond | 75.1% ↗ | 71.92% ↗ | +3.2 pt | Kimi K2 |
| Only Kimi K2 reports · 17 | ||||
| MMLU-Pro | 81.1% ↗ | not reported | — | — |
| AIME 2025 | 49.5% ↗ | not reported | — | — |
| Aider-Polyglot | 60% ↗ | not reported | — | — |
| GSO Opt@1 (GSO) | 2% ↗ | not reported | — | — |
| Humanity's Last Exam (Text Only) | 4.7% ↗ | not reported | — | — |
| IFEval (Prompt Strict) | 89.8% ↗ | not reported | — | — |
| LiveCodeBench v6 (Aug 24 - May 25) | 53.7% ↗ | not reported | — | — |
| MMLU-Redux | 92.7% ↗ | not reported | — | — |
| SimpleBench (SimpleBench) | 26.3% ↗ | not reported | — | — |
| SimpleQA | 31% ↗ | not reported | — | — |
| SWE-bench Multilingual (Agentic Coding, single attempt) | 47.3% ↗ | not reported | — | — |
| SWE-bench Verified (Agentic Coding, single attempt) | 65.8% ↗ | not reported | — | — |
| Tau2 airline | 56.5% ↗ | not reported | — | — |
| Tau2 retail | 70.6% ↗ | not reported | — | — |
| Tau2 telecom | 65.8% ↗ | not reported | — | — |
| TerminalBench (Inhouse Framework) | 30% ↗ | not reported | — | — |
| WeirdML (Håvard Tveit Ihle) | 39.4% ↗ | not reported | — | — |
| Only Solar Pro 3 reports · 11 | ||||
| AIME'26 | not reported | 83% ↗ | — | — |
| Arena-hard-v2 | not reported | 74.7% ↗ | — | — |
| HLE | not reported | 11.91% ↗ | — | — |
| HMMT'26 | not reported | 65.91% ↗ | — | — |
| IFBench | not reported | 73.13% ↗ | — | — |
| Ko-Arena-hard-v2 | not reported | 78.2% ↗ | — | — |
| LCB.v1-6 | not reported | 77.73% ↗ | — | — |
| MMLU PRO (0shot, cot) | not reported | 81.24% ↗ | — | — |
| SWE Bench | not reported | 28.57% ↗ | — | — |
| Tau2-all | not reported | 72.34% ↗ | — | — |
| Terminal Bench 2 | not reported | 10.11% ↗ | — | — |
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 minus Solar Pro 3 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 | Solar Pro 3 | Edge |
|---|---|---|---|
| Context window | 128K tokens | 128K tokens | Tie |
| Max output | — | — | — |
| Input price / 1M | — | $0.15 ↗ | — |
| Output price / 1M | — | $0.6 ↗ | — |
| Cached input / 1M | — | $0.015 ↗ | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | — | $0.75 | — |
| Modalities | text | text | Tie |
| Released | 2025-07-11 | 2026-01-26 | — |
| Cited benchmark scores | 18 | 12 | — |
Reliability
Provider status
Live from /statusMore matchups
Kimi K2 vs …
Models sharing the most benchmarksMore matchups
Solar Pro 3 vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Kimi K2 and Solar Pro 3 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.