Model comparison
GPT-4.1 mini vs Kimi K2.5
Head-to-head evidence from 21 shared benchmark results across 7 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: GPT-4.1 mini #160 (Estimated); Kimi K2.5 #59 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. GPT-4.1 mini and Kimi K2.5 share 21 comparable benchmark results. 4 of 8 categories are comparable. 1 result is unique to GPT-4.1 mini; 42 to Kimi K2.5.
Updated July 24, 2026- Shared results
- 21
- GPT-4.1 mini only
- 1
- Kimi K2.5 only
- 42
- Comparable categories
- 4 / 8
Pick Kimi K2.5 if you want the stronger benchmark profile. GPT-4.1 mini only becomes the better choice if knowledge is the priority or you want the cheaper token bill.
Confidence note. This is a partial-evidence comparison with 21 shared benchmark results across 7 evidence categories; 4 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 43.1. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Kimi K2.5's sharpest advantage is in mathematics, where it averages 60.6 against 4.5. The single biggest benchmark swing on the page is SWE-bench Verified, 23.6% to 76.8%. GPT-4.1 mini does hit back in knowledge, so the answer changes if that is the part of the workload you care about most.
Kimi K2.5 is also the more expensive model on tokens at $0.60 input / $3.00 output per 1M tokens, versus $0.40 input / $1.60 output per 1M tokens for GPT-4.1 mini. GPT-4.1 mini gives you the larger context window at 1M, compared with 256K for Kimi K2.5.
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 | GPT-4.1 mini | Δ | Kimi K2.5 |
|---|---|---|---|
| Math | GPT-4.1 mini4.5 | Margin→ 56.1 | Kimi K2.560.6 |
| Coding | GPT-4.1 mini23.6 | Margin→ 35.8 | Kimi K2.559.4 |
| Knowledge | GPT-4.1 mini64.2 | Margin← 7.3 | Kimi K2.556.9 |
| Inst. Following | GPT-4.1 mini88.5 | Margin→ 5.4 | Kimi K2.593.9 |
| Agentic | GPT-4.1 miniNot measured | MarginNo overlap | Kimi K2.555.0 |
| Reasoning | GPT-4.1 miniNot measured | MarginNo overlap | Kimi K2.561.0 |
| Multilingual | GPT-4.1 miniNot measured | MarginNo overlap | Kimi K2.582.3 |
| Multimodal | GPT-4.1 miniNot measured | MarginNo overlap | Kimi K2.578.5 |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
SWE-bench Verified
CodingA 23.6%B 76.8%Winner: Kimi K2.5Δ 53.2SWE-bench Verified: GPT-4.1 mini scored 23.6%; Kimi K2.5 scored 76.8%. Kimi K2.5 wins this benchmark. - Source ↗
FrontierMath v2 (Tiers 1-3)
MathA 4.483%B 27.900%Winner: Kimi K2.5Δ 23.4FrontierMath v2 (Tiers 1-3): GPT-4.1 mini scored 4.483%; Kimi K2.5 scored 27.900%. Kimi K2.5 wins this benchmark. - Source ↗
GPQA
KnowledgeA 64.2%B 87.6%Winner: Kimi K2.5Δ 23.4GPQA: GPT-4.1 mini scored 64.2%; Kimi K2.5 scored 87.6%. Kimi K2.5 wins this benchmark. - Source ↗
IFEval
Inst. FollowingA 88.5%B 93.9%Winner: Kimi K2.5Δ 5.4IFEval: GPT-4.1 mini scored 88.5%; Kimi K2.5 scored 93.9%. Kimi K2.5 wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | GPT-4.1 mini | Kimi K2.5 | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | GPT-4.1 mini$0.4 input / $1.6 output | Kimi K2.5$0.6 input / $3 output | GPT-4.1 mini has the lower combined listed price. |
| Generation speedtokens per second | GPT-4.1 mini80 tok/s | Kimi K2.545 tok/s | GPT-4.1 mini has the higher measured throughput. |
| First-answer latencyseconds to first token | GPT-4.1 mini0.76 s | Kimi K2.52.38 s | GPT-4.1 mini reaches the first token sooner. |
| Context windowmaximum listed tokens | GPT-4.1 mini1M | Kimi K2.5256K | GPT-4.1 mini lists the larger context window. |
Benchmark Deep Dive
Agentic19 benchmarks
| Benchmark | GPT-4.1 mini | Kimi K2.5 | Result |
|---|---|---|---|
| AA Agentic IndexSource | 1.7% | 21.7% | Kimi K2.5 leads |
| τ²-bench resultsSource | 52.9% | 95.9% | Kimi K2.5 leads |
| GDPval-AASource | 0.4% | 25.1% | Kimi K2.5 leads |
| GDPval-AASource | 508 | 1003 | Kimi K2.5 leads |
| 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 |
| APEX-Agents-AASource | — | 11.5% | Not comparable |
| Gert LabsSource | — | 45.88% | Not comparable |
| ResearchClawBenchSource | — | 14.0% | Not comparable |
| JobBenchSource | — | 8.7% | Not comparable |
CodingKimi K2.5 wins10 benchmarks
| Benchmark | GPT-4.1 mini | Kimi K2.5 | Result |
|---|---|---|---|
| SWE-bench VerifiedSource | 23.6% | 76.8% | Kimi K2.5 leads |
| AA Coding IndexSource | 20.2% | 46.8% | Kimi K2.5 leads |
| AA-SciCodeSource | 40.4% | 49.0% | Kimi K2.5 leads |
| 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 |
Reasoning3 benchmarks
KnowledgeGPT-4.1 mini wins13 benchmarks
| Benchmark | GPT-4.1 mini | Kimi K2.5 | Result |
|---|---|---|---|
| MMLUSource | 87.5% | — | Not comparable |
| GPQASource | 64.2% | 87.6% | Kimi K2.5 leads |
| Artificial Analysis Intelligence IndexSource | 14.8% | 35.4% | Kimi K2.5 leads |
| AA-GPQA DiamondSource | 66.4% | 87.9% | Kimi K2.5 leads |
| AA-HLESource | 4.6% | 29.4% | Kimi K2.5 leads |
| AA-Omniscience IndexSource | -50.1% | -8.1% | Kimi K2.5 leads |
| AA-Omniscience AccuracySource | 17.5% | 34.3% | Kimi K2.5 leads |
| AA-Omniscience Hallucination RateSource | 82.0% | 64.6% | 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 |
MathKimi K2.5 wins9 benchmarks
| Benchmark | GPT-4.1 mini | Kimi K2.5 | Result |
|---|---|---|---|
| FrontierMath v2 (Tiers 1-3)Source | 4.483% | 27.900% | Kimi K2.5 leads |
| 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 (Tier 4)Source | — | 4.200% | Not comparable |
Multilingual2 benchmarks
Multimodal6 benchmarks
Frequently Asked Questions (5)
Which is better, GPT-4.1 mini or Kimi K2.5?
Kimi K2.5 is ahead on BenchLM's BenchAlign leaderboard, 58.83 to 43.1. The biggest single separator in this matchup is SWE-bench Verified, where the scores are 23.6% and 76.8%.
Which is better for knowledge tasks, GPT-4.1 mini or Kimi K2.5?
GPT-4.1 mini has the edge for knowledge tasks in this comparison, averaging 64.2 versus 56.9. Inside this category, AA-Omniscience Index is the benchmark that creates the most daylight between them.
Which is better for coding, GPT-4.1 mini or Kimi K2.5?
Kimi K2.5 has the edge for coding in this comparison, averaging 59.4 versus 23.6. Inside this category, SWE-bench Verified is the benchmark that creates the most daylight between them.
Which is better for math, GPT-4.1 mini or Kimi K2.5?
Kimi K2.5 has the edge for math in this comparison, averaging 60.6 versus 4.5. Inside this category, FrontierMath v2 (Tiers 1-3) is the benchmark that creates the most daylight between them.
Which is better for instruction following, GPT-4.1 mini or Kimi K2.5?
Kimi K2.5 has the edge for instruction following in this comparison, averaging 93.9 versus 88.5. Inside this category, AA-IFBench 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.