Model comparison
GPT-5.4 vs Kimi K2
Head-to-head evidence from 14 shared benchmark results across 7 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: GPT-5.4 #8 (Supported); Kimi K2 #189 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. GPT-5.4 and Kimi K2 share 14 comparable benchmark results. 1 of 8 categories are comparable. 38 results are unique to GPT-5.4; 0 to Kimi K2.
Updated July 20, 2026- Shared results
- 14
- GPT-5.4 only
- 38
- Kimi K2 only
- 0
- Comparable categories
- 1 / 8
Pick GPT-5.4 if you want the stronger benchmark profile. Kimi K2 only becomes the better choice if you want the cheaper token bill or you would rather avoid the extra latency and token burn of a reasoning model.
Confidence note. This is a partial-evidence comparison with 14 shared benchmark results across 7 evidence categories; 1 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 27.19. 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 mathematics, where it averages 42.5 against 16.1. The single biggest benchmark swing on the page is FrontierMath v2 (Tier 4), 27.100% to 0.000%.
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 / $2.50 output per 1M tokens for Kimi K2. That is roughly 6.0x on output cost alone. GPT-5.4 is the reasoning model in the pair, while Kimi K2 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. GPT-5.4 gives you the larger context window at 1.05M, compared with 128K for Kimi K2.
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 |
|---|---|---|---|
| Math | GPT-5.442.5 | Margin← 26.4 | Kimi K216.1 |
| Agentic | GPT-5.477.2 | MarginNo overlap | Kimi K2Not measured |
| Coding | GPT-5.457.7 | MarginNo overlap | Kimi K2Not measured |
| Knowledge | GPT-5.457.6 | MarginNo overlap | Kimi K2Not measured |
| Multimodal | GPT-5.473.2 | MarginNo overlap | Kimi K2Not measured |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
FrontierMath v2 (Tier 4)
MathA 27.100%B 0.000%Winner: GPT-5.4Δ 27.1FrontierMath v2 (Tier 4): GPT-5.4 scored 27.100%; Kimi K2 scored 0.000%. GPT-5.4 wins this benchmark. - Source ↗
FrontierMath v2 (Tiers 1-3)
MathA 47.600%B 21.404%Winner: GPT-5.4Δ 26.2FrontierMath v2 (Tiers 1-3): GPT-5.4 scored 47.600%; Kimi K2 scored 21.404%. 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 | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | GPT-5.4$2.5 input / $15 output | Kimi K2$0.6 input / $2.5 output | Kimi K2 has the lower combined listed price. |
| Generation speedtokens per second | GPT-5.474 tok/s | Kimi K243 tok/s | GPT-5.4 has the higher measured throughput. |
| First-answer latencyseconds to first token | GPT-5.4151.79 s | Kimi K21.51 s | Kimi K2 reaches the first token sooner. |
| Context windowmaximum listed tokens | GPT-5.41.05M | Kimi K2128K | GPT-5.4 lists the larger context window. |
Benchmark Deep Dive
Agentic17 benchmarks
| Benchmark | GPT-5.4 | Kimi K2 | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 75.1% | — | Not comparable |
| CyberGymSource | 79.0% | — | Not comparable |
| BrowseCompSource | 82.7% | — | Not comparable |
| OSWorld-VerifiedSource | 75% | — | Not comparable |
| MCP AtlasSource | 70.6% | — | Not comparable |
| ToolathlonSource | 54.6% | — | Not comparable |
| τ²-bench resultsSource | 87.1% | 61.1% | GPT-5.4 leads |
| Claw-EvalSource | 60.3% | — | Not comparable |
| DeepSearchQASource | 73.6% | — | Not comparable |
| AA Agentic IndexSource | 41.1% | — | Not comparable |
| APEX-Agents-AASource | 33.3% | — | Not comparable |
| GDPval-AASource | 44.7% | — | Not comparable |
| GDPval-AASource | 1395 | — | Not comparable |
| Gert LabsSource | 64.89% | — | Not comparable |
| ResearchClawBenchSource | 15.3% | — | Not comparable |
| JobBenchSource | 38.9% | — | Not comparable |
| ExploitGymSource | 6.0% | — | Not comparable |
Coding6 benchmarks
Reasoning2 benchmarks
Knowledge13 benchmarks
| Benchmark | GPT-5.4 | Kimi K2 | Result |
|---|---|---|---|
| GPQASource | 92.8% | — | Not comparable |
| 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% | 19.4% | GPT-5.4 leads |
| AA-GPQA DiamondSource | 92.0% | 76.6% | GPT-5.4 leads |
| AA-HLESource | 41.6% | 7.0% | GPT-5.4 leads |
| AA-Omniscience IndexSource | 5.7% | -27.5% | GPT-5.4 leads |
| AA-Omniscience AccuracySource | 50.0% | 26.8% | GPT-5.4 leads |
| AA-Omniscience Hallucination RateSource | 88.6% | 74.2% | Kimi K2 leads |
| HealthBench ProfessionalSource | 48.1% | — | Not comparable |
MathGPT-5.4 wins2 benchmarks
Multimodal11 benchmarks
| Benchmark | GPT-5.4 | Kimi K2 | Result |
|---|---|---|---|
| MMMU-ProSource | 81.2% | — | Not comparable |
| 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% | — | Not comparable |
| Design Arena WebsiteSource | 1252 | 1083 | GPT-5.4 leads |
Inst. Following1 benchmarks
| Benchmark | GPT-5.4 | Kimi K2 | Result |
|---|---|---|---|
| AA-IFBenchSource | 73.9% | 41.5% | GPT-5.4 leads |
Frequently Asked Questions (2)
Which is better, GPT-5.4 or Kimi K2?
GPT-5.4 is ahead on BenchLM's BenchAlign leaderboard, 74.24 to 27.19. The biggest single separator in this matchup is FrontierMath v2 (Tier 4), where the scores are 27.100% and 0.000%.
Which is better for math, GPT-5.4 or Kimi K2?
GPT-5.4 has the edge for math in this comparison, averaging 42.5 versus 16.1. Inside this category, FrontierMath v2 (Tier 4) 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.