Model comparison
Kimi K2.5 vs o1-pro
Head-to-head evidence from 2 shared benchmark results across 1 category. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: Kimi K2.5 #59 (Supported); o1-pro #148 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. Kimi K2.5 and o1-pro share 2 comparable benchmark results. 1 of 8 categories are comparable. 61 results are unique to Kimi K2.5; 0 to o1-pro.
Updated July 24, 2026- Shared results
- 2
- Kimi K2.5 only
- 61
- o1-pro only
- 0
- Comparable categories
- 1 / 8
Pick Kimi K2.5 if you want the stronger benchmark profile. o1-pro only becomes the better choice if knowledge is the priority or you want the stronger reasoning-first profile.
Confidence note. This is a partial-evidence comparison with 2 shared benchmark results across 1 evidence category; 1 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
Kimi K2.5 is clearly ahead on the BenchAlign aggregate, 58.83 to 45.03. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
o1-pro is also the more expensive model on tokens at $150.00 input / $600.00 output per 1M tokens, versus $0.60 input / $3.00 output per 1M tokens for Kimi K2.5. That is roughly 200.0x on output cost alone. o1-pro is the reasoning model in the pair, while Kimi K2.5 is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. Kimi K2.5 gives you the larger context window at 256K, compared with 200K for o1-pro.
Category breakdown
Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.
| Category | Kimi K2.5 | Δ | o1-pro |
|---|---|---|---|
| Knowledge | Kimi K2.556.9 | Margin→ 22.1 | o1-pro79.0 |
| Agentic | Kimi K2.555.0 | MarginNo overlap | o1-proNot measured |
| Coding | Kimi K2.559.4 | MarginNo overlap | o1-proNot measured |
| Reasoning | Kimi K2.561.0 | MarginNo overlap | o1-proNot measured |
| Math | Kimi K2.560.6 | MarginNo overlap | o1-proNot measured |
| Multilingual | Kimi K2.582.3 | MarginNo overlap | o1-proNot measured |
| Multimodal | Kimi K2.578.5 | MarginNo overlap | o1-proNot measured |
| Inst. Following | Kimi K2.593.9 | MarginNo overlap | o1-proNot measured |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
GPQA
KnowledgeA 87.6%B 79%Winner: Kimi K2.5Δ 8.6GPQA: Kimi K2.5 scored 87.6%; o1-pro scored 79%. Kimi K2.5 wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | Kimi K2.5 | o1-pro | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Kimi K2.5$0.6 input / $3 output | o1-pro$150 input / $600 output | Kimi K2.5 has the lower combined listed price. |
| Generation speedtokens per second | Kimi K2.545 tok/s | o1-proNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | Kimi K2.52.38 s | o1-proNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | Kimi K2.5256K | o1-pro200K | Kimi K2.5 lists the larger context window. |
Benchmark Deep Dive
Agentic19 benchmarks
| Benchmark | Kimi K2.5 | o1-pro | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 50.8% | — | Not comparable |
| BrowseCompSource | 60.6% | — | Not comparable |
| Claw-EvalSource | 52.3% | — | Not comparable |
| QwenClawBenchSource | 54.3% | — | Not comparable |
| τ³-bench resultsSource | 65.7% | — | Not comparable |
| DeepSearchQASource | 77.1% | — | Not comparable |
| DeepPlanningSource | 14.4% | — | Not comparable |
| ToolathlonSource | 27.8% | — | Not comparable |
| MCP AtlasSource | 29.5% | — | Not comparable |
| MCP-TasksSource | 59.1% | — | Not comparable |
| WideResearchSource | 72.7% | — | Not comparable |
| τ²-bench resultsSource | 95.9% | — | Not comparable |
| APEX-Agents-AASource | 11.5% | — | Not comparable |
| Gert LabsSource | 45.88% | — | Not comparable |
| ResearchClawBenchSource | 14.0% | — | Not comparable |
| JobBenchSource | 8.7% | — | Not comparable |
| AA Agentic IndexSource | 21.7% | — | Not comparable |
| GDPval-AASource | 25.1% | — | Not comparable |
| GDPval-AASource | 1003 | — | Not comparable |
Coding10 benchmarks
| Benchmark | Kimi K2.5 | o1-pro | Result |
|---|---|---|---|
| SWE-bench VerifiedSource | 76.8% | — | Not comparable |
| SWE-bench Verified*Source | 70.8% | — | Not comparable |
| LiveCodeBench v6Source | 85.0% | — | Not comparable |
| SWE-bench ProSource | 50.7% | — | Not comparable |
| SWE MultilingualSource | 73% | — | Not comparable |
| SWE-RebenchSource | 58.5% | — | Not comparable |
| React Native EvalsSource | 77.2% | — | Not comparable |
| SciCodeSource | 48.7% | — | Not comparable |
| AA-SciCodeSource | 49.0% | — | Not comparable |
| AA Coding IndexSource | 46.8% | — | Not comparable |
Reasoning3 benchmarks
Knowledgeo1-pro wins12 benchmarks
| Benchmark | Kimi K2.5 | o1-pro | Result |
|---|---|---|---|
| GPQASource | 87.6% | 79% | Kimi K2.5 leads |
| GPQA-DSource | 87.6% | — | Not comparable |
| SuperGPQASource | 69.2% | — | Not comparable |
| MMLU-ProSource | 87.1% | — | Not comparable |
| MMLU-Pro (Arcee)Source | 87.1% | — | Not comparable |
| HLESource | 30.1% | — | Not comparable |
| Artificial Analysis Intelligence IndexSource | 35.4% | 18.9% | Kimi K2.5 leads |
| AA-GPQA DiamondSource | 87.9% | — | Not comparable |
| AA-HLESource | 29.4% | — | Not comparable |
| AA-Omniscience IndexSource | -8.1% | — | Not comparable |
| AA-Omniscience AccuracySource | 34.3% | — | Not comparable |
| AA-Omniscience Hallucination RateSource | 64.6% | — | Not comparable |
Math9 benchmarks
| Benchmark | Kimi K2.5 | o1-pro | Result |
|---|---|---|---|
| AIME 2025Source | 96.1% | — | Not comparable |
| AIME26Source | 95.8% | — | Not comparable |
| AIME25 (Arcee)Source | 96.3% | — | Not comparable |
| HMMT Feb 2025Source | 95.4% | — | Not comparable |
| HMMT Nov 2025Source | 91.1% | — | Not comparable |
| HMMT Feb 2026Source | 87.1% | — | Not comparable |
| MMAnswerBenchSource | 81.8% | — | Not comparable |
| FrontierMath v2 (Tiers 1-3)Source | 27.900% | — | Not comparable |
| FrontierMath v2 (Tier 4)Source | 4.200% | — | Not comparable |
Multilingual2 benchmarks
Multimodal6 benchmarks
Frequently Asked Questions (2)
Which is better, Kimi K2.5 or o1-pro?
Kimi K2.5 is ahead on BenchLM's BenchAlign leaderboard, 58.83 to 45.03. The biggest single separator in this matchup is GPQA, where the scores are 87.6% and 79%.
Which is better for knowledge tasks, Kimi K2.5 or o1-pro?
o1-pro has the edge for knowledge tasks in this comparison, averaging 79 versus 56.9. Inside this category, Artificial Analysis Intelligence Index is the benchmark that creates the most daylight between them.
Self-host vs API cost
Estimates at 50,000 req/day · 1000 tokens/req average.