Model comparison
GPT-5.4 vs Kimi K2.5 (Reasoning)
Head-to-head evidence from 24 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: GPT-5.4 #8 (Supported); Kimi K2.5 (Reasoning) #57 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. GPT-5.4 and Kimi K2.5 (Reasoning) share 24 comparable benchmark results. 4 of 8 categories are comparable. 28 results are unique to GPT-5.4; 3 to Kimi K2.5 (Reasoning).
Updated July 20, 2026- Shared results
- 24
- GPT-5.4 only
- 28
- Kimi K2.5 (Reasoning) only
- 3
- Comparable categories
- 4 / 8
Pick GPT-5.4 if you want the stronger benchmark profile. Kimi K2.5 (Reasoning) 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 24 shared benchmark results across 6 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
GPT-5.4 is clearly ahead on the BenchAlign aggregate, 74.24 to 59.35. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
GPT-5.4's sharpest advantage is in agentic, where it averages 77.2 against 55. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 75.1% to 50.8%. Kimi K2.5 (Reasoning) does hit back in knowledge, so the answer changes if that is the part of the workload you care about most.
GPT-5.4 is also the more expensive model on tokens at $2.50 input / $15.00 output per 1M tokens, versus $0.60 input / $3.00 output per 1M tokens for Kimi K2.5 (Reasoning). That is roughly 5.0x on output cost alone. GPT-5.4 gives you the larger context window at 1.05M, compared with 128K for Kimi K2.5 (Reasoning).
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-5.4 | Δ | Kimi K2.5 (Reasoning) |
|---|---|---|---|
| Knowledge | GPT-5.457.6 | Margin→ 29.6 | Kimi K2.5 (Reasoning)87.2 |
| Agentic | GPT-5.477.2 | Margin← 22.2 | Kimi K2.5 (Reasoning)55.0 |
| Coding | GPT-5.457.7 | Margin→ 19.1 | Kimi K2.5 (Reasoning)76.8 |
| Multimodal | GPT-5.473.2 | Margin→ 5.3 | Kimi K2.5 (Reasoning)78.5 |
| Math | GPT-5.442.5 | MarginNo overlap | Kimi K2.5 (Reasoning)Not measured |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
Terminal-Bench 2.0
AgenticA 75.1%B 50.8%Winner: GPT-5.4Δ 24.3Terminal-Bench 2.0: GPT-5.4 scored 75.1%; Kimi K2.5 (Reasoning) scored 50.8%. GPT-5.4 wins this benchmark. - Source ↗
BrowseComp
AgenticA 82.7%B 60.6%Winner: GPT-5.4Δ 22.1BrowseComp: GPT-5.4 scored 82.7%; Kimi K2.5 (Reasoning) scored 60.6%. GPT-5.4 wins this benchmark. - Source ↗
GPQA
KnowledgeA 92.8%B 87.6%Winner: GPT-5.4Δ 5.2GPQA: GPT-5.4 scored 92.8%; Kimi K2.5 (Reasoning) scored 87.6%. GPT-5.4 wins this benchmark. - Source ↗
MMMU-Pro
MultimodalA 81.2%B 78.5%Winner: GPT-5.4Δ 2.7MMMU-Pro: GPT-5.4 scored 81.2%; Kimi K2.5 (Reasoning) scored 78.5%. GPT-5.4 wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | GPT-5.4 | Kimi K2.5 (Reasoning) | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | GPT-5.4$2.5 input / $15 output | Kimi K2.5 (Reasoning)$0.6 input / $3 output | Kimi K2.5 (Reasoning) has the lower combined listed price. |
| Generation speedtokens per second | GPT-5.474 tok/s | Kimi K2.5 (Reasoning)Not available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | GPT-5.4151.79 s | Kimi K2.5 (Reasoning)Not available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | GPT-5.41.05M | Kimi K2.5 (Reasoning)128K | GPT-5.4 lists the larger context window. |
Benchmark Deep Dive
AgenticGPT-5.4 wins17 benchmarks
| Benchmark | GPT-5.4 | Kimi K2.5 (Reasoning) | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 75.1% | 50.8% | GPT-5.4 leads |
| CyberGymSource | 79.0% | — | Not comparable |
| BrowseCompSource | 82.7% | 60.6% | GPT-5.4 leads |
| OSWorld-VerifiedSource | 75% | — | Not comparable |
| MCP AtlasSource | 70.6% | — | Not comparable |
| ToolathlonSource | 54.6% | — | Not comparable |
| τ²-bench resultsSource | 87.1% | 95.9% | Kimi K2.5 (Reasoning) leads |
| Claw-EvalSource | 60.3% | — | Not comparable |
| DeepSearchQASource | 73.6% | — | Not comparable |
| AA Agentic IndexSource | 41.1% | 21.7% | GPT-5.4 leads |
| APEX-Agents-AASource | 33.3% | 11.5% | GPT-5.4 leads |
| GDPval-AASource | 44.7% | 25.4% | GPT-5.4 leads |
| GDPval-AASource | 1395 | 1009 | GPT-5.4 leads |
| Gert LabsSource | 64.89% | 32.58% | GPT-5.4 leads |
| ResearchClawBenchSource | 15.3% | — | Not comparable |
| JobBenchSource | 38.9% | — | Not comparable |
| ExploitGymSource | 6.0% | — | Not comparable |
CodingKimi K2.5 (Reasoning) wins7 benchmarks
| Benchmark | GPT-5.4 | Kimi K2.5 (Reasoning) | Result |
|---|---|---|---|
| LiveCodeBench ProSource | 87.5% | — | Not comparable |
| SWE-bench ProSource | 57.7% | — | Not comparable |
| React Native EvalsSource | 85.3% | — | Not comparable |
| Vibe Code BenchSource | 67.42% | 17.54% | GPT-5.4 leads |
| AA Coding IndexSource | 71.0% | 46.8% | GPT-5.4 leads |
| AA-SciCodeSource | 56.6% | 49.0% | GPT-5.4 leads |
| SWE-bench VerifiedSource | — | 76.8% | Not comparable |
Reasoning2 benchmarks
KnowledgeKimi K2.5 (Reasoning) wins14 benchmarks
| Benchmark | GPT-5.4 | Kimi K2.5 (Reasoning) | Result |
|---|---|---|---|
| GPQASource | 92.8% | 87.6% | GPT-5.4 leads |
| HLESource | 52.1% | — | Not comparable |
| HLE w/o toolsSource | 39.8% | — | Not comparable |
| GPQA-DSource | 92.8% | — | Not comparable |
| HealthBench HardSource | 40.1% | — | Not comparable |
| MedXpertQA (Text)Source | 59.6% | — | Not comparable |
| Artificial Analysis Intelligence IndexSource | 51.4% | 35.4% | GPT-5.4 leads |
| AA-GPQA DiamondSource | 92.0% | 87.9% | GPT-5.4 leads |
| AA-HLESource | 41.6% | 29.4% | GPT-5.4 leads |
| AA-Omniscience IndexSource | 5.7% | -8.1% | GPT-5.4 leads |
| AA-Omniscience AccuracySource | 50.0% | 34.3% | GPT-5.4 leads |
| AA-Omniscience Hallucination RateSource | 88.6% | 64.6% | Kimi K2.5 (Reasoning) leads |
| HealthBench ProfessionalSource | 48.1% | — | Not comparable |
| MMLU-ProSource | — | 87.1% | Not comparable |
Math3 benchmarks
MultimodalKimi K2.5 (Reasoning) wins11 benchmarks
| Benchmark | GPT-5.4 | Kimi K2.5 (Reasoning) | Result |
|---|---|---|---|
| MMMU-ProSource | 81.2% | 78.5% | GPT-5.4 leads |
| OfficeQA ProSource | 53.2% | — | Not comparable |
| MMMU-Pro w/ PythonSource | 82.1% | — | Not comparable |
| CharXivSource | 82.8% | — | Not comparable |
| ERQASource | 65.4% | — | Not comparable |
| SimpleVQASource | 61.1% | — | Not comparable |
| ScreenSpot ProSource | 85.4% | — | Not comparable |
| ZeroBenchSource | 41.0% | — | Not comparable |
| MedXpertQA (MM)Source | 77.1% | — | Not comparable |
| AA-MMMU-ProSource | 78.4% | 75.4% | GPT-5.4 leads |
| Design Arena WebsiteSource | 1252 | 1282 | Kimi K2.5 (Reasoning) leads |
Inst. Following1 benchmarks
| Benchmark | GPT-5.4 | Kimi K2.5 (Reasoning) | Result |
|---|---|---|---|
| AA-IFBenchSource | 73.9% | 70.2% | GPT-5.4 leads |
Frequently Asked Questions (5)
Which is better, GPT-5.4 or Kimi K2.5 (Reasoning)?
GPT-5.4 is ahead on BenchLM's BenchAlign leaderboard, 74.24 to 59.35. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 75.1% and 50.8%.
Which is better for knowledge tasks, GPT-5.4 or Kimi K2.5 (Reasoning)?
Kimi K2.5 (Reasoning) has the edge for knowledge tasks in this comparison, averaging 87.2 versus 57.6. Inside this category, AA-Omniscience Hallucination Rate is the benchmark that creates the most daylight between them.
Which is better for coding, GPT-5.4 or Kimi K2.5 (Reasoning)?
Kimi K2.5 (Reasoning) has the edge for coding in this comparison, averaging 76.8 versus 57.7. Inside this category, Vibe Code Bench is the benchmark that creates the most daylight between them.
Which is better for agentic tasks, GPT-5.4 or Kimi K2.5 (Reasoning)?
GPT-5.4 has the edge for agentic tasks in this comparison, averaging 77.2 versus 55. Inside this category, GDPval-AA is the benchmark that creates the most daylight between them.
Which is better for multimodal and grounded tasks, GPT-5.4 or Kimi K2.5 (Reasoning)?
Kimi K2.5 (Reasoning) has the edge for multimodal and grounded tasks in this comparison, averaging 78.5 versus 73.2. Inside this category, Design Arena Website is the benchmark that creates the most daylight between them.
Related Comparisons
Explore More
Choose a model with this week’s evidence
Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.
One email each week. Unsubscribe anytime.