Model comparison
GPT-5.4 Pro vs Kimi K3
Head-to-head evidence from 5 shared benchmark results across 4 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: GPT-5.4 Pro #44 (Estimated); Kimi K3 #4 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. GPT-5.4 Pro and Kimi K3 share 5 comparable benchmark results. 3 of 8 categories are comparable. 7 results are unique to GPT-5.4 Pro; 52 to Kimi K3.
Updated July 23, 2026- Shared results
- 5
- GPT-5.4 Pro only
- 7
- Kimi K3 only
- 52
- Comparable categories
- 3 / 8
Pick Kimi K3 if you want the stronger benchmark profile. GPT-5.4 Pro only becomes the better choice if multimodal & grounded is the priority.
Confidence note. This is a partial-evidence comparison with 5 shared benchmark results across 4 evidence categories; 3 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
Kimi K3 is clearly ahead on the BenchAlign aggregate, 80.96 to 60.89. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Kimi K3's sharpest advantage is in knowledge, where it averages 61 against 58.7. The single biggest benchmark swing on the page is MMMU-Pro, 94% to 81.6%. GPT-5.4 Pro does hit back in multimodal & grounded, so the answer changes if that is the part of the workload you care about most.
GPT-5.4 Pro is also the more expensive model on tokens at $30.00 input / $180.00 output per 1M tokens, versus $3.00 input / $15.00 output per 1M tokens for Kimi K3. That is roughly 12.0x on output cost alone.
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 Pro | Δ | Kimi K3 |
|---|---|---|---|
| Multimodal | GPT-5.4 Pro94.0 | Margin← 15.5 | Kimi K378.5 |
| Knowledge | GPT-5.4 Pro58.7 | Margin→ 2.3 | Kimi K361.0 |
| Agentic | GPT-5.4 Pro89.3 | Margin→ 0.2 | Kimi K389.5 |
| Reasoning | GPT-5.4 Pro83.3 | MarginNo overlap | Kimi K3Not measured |
| Math | GPT-5.4 Pro46.9 | MarginNo overlap | Kimi K3Not measured |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
MMMU-Pro
MultimodalA 94%B 81.6%Winner: GPT-5.4 ProΔ 12.4MMMU-Pro: GPT-5.4 Pro scored 94%; Kimi K3 scored 81.6%. GPT-5.4 Pro wins this benchmark. - Source ↗
HLE
KnowledgeA 58.7%B 56%Winner: GPT-5.4 ProΔ 2.7HLE: GPT-5.4 Pro scored 58.7%; Kimi K3 scored 56%. GPT-5.4 Pro wins this benchmark. - Source ↗
BrowseComp
AgenticA 89.3%B 91.2%Winner: Kimi K3Δ 1.9BrowseComp: GPT-5.4 Pro scored 89.3%; Kimi K3 scored 91.2%. Kimi K3 wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | GPT-5.4 Pro | Kimi K3 | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | GPT-5.4 Pro$30 input / $180 output | Kimi K3$3 input / $15 output | Kimi K3 has the lower combined listed price. |
| Generation speedtokens per second | GPT-5.4 Pro74 tok/s | Kimi K3Not available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | GPT-5.4 Pro151.79 s | Kimi K3Not available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | GPT-5.4 Pro1.05M | Kimi K31.05M | Listed context windows are equal. |
Benchmark Deep Dive
AgenticKimi K3 wins21 benchmarks
| Benchmark | GPT-5.4 Pro | Kimi K3 | Result |
|---|---|---|---|
| BrowseCompSource | 89.3% | 91.2% | Kimi K3 leads |
| Terminal-Bench 2.0Source | — | 88.3% | Not comparable |
| DeepSearchQASource | — | 95.0% | Not comparable |
| Toolathlon-VerifiedSource | — | 73.2% | Not comparable |
| MCP AtlasSource | — | 84.2% | Not comparable |
| AutomationBenchSource | — | 30.8% | Not comparable |
| JobBenchSource | — | 52.9% | Not comparable |
| APEX-AgentsSource | — | 37.6% | Not comparable |
| SpreadsheetBench 2Source | — | 34.8% | Not comparable |
| DECK-BenchSource | — | 73.5% | Not comparable |
| AA Agentic IndexSource | — | 50.1% | Not comparable |
| GDPval-AASource | — | 59.0% | Not comparable |
| GDPval-AASource | — | 1679 | Not comparable |
| AA BriefcaseSource | — | 1543 | Not comparable |
| AA AutomationBenchSource | — | 52.7% | Not comparable |
| AA EnterpriseOps-GymSource | — | 45.3% | Not comparable |
| AA Harvey LABSource | — | 94.6% | Not comparable |
| AA Tau3 BankingSource | — | 33.4% | Not comparable |
| aaTerminalBench21Source | — | 85% | Not comparable |
| APEX-Agents-AASource | — | 41.3% | Not comparable |
| AA ITBenchSource | — | 47.7% | Not comparable |
Coding9 benchmarks
| Benchmark | GPT-5.4 Pro | Kimi K3 | Result |
|---|---|---|---|
| deepSweSource | — | 67.5% | Not comparable |
| FrontierSWESource | — | 81.2% | Not comparable |
| ProgramBenchSource | — | 77.8% | Not comparable |
| Kimi Code Bench v2Source | — | 72.9% | Not comparable |
| sweMarathonSource | — | 42% | Not comparable |
| PostTrain BenchSource | — | 36.6% | Not comparable |
| MLS-Bench LiteSource | — | 48.3% | Not comparable |
| AA Coding IndexSource | — | 76.2% | Not comparable |
| AA-SciCodeSource | — | 58.7% | Not comparable |
Reasoning3 benchmarks
KnowledgeKimi K3 wins12 benchmarks
| Benchmark | GPT-5.4 Pro | Kimi K3 | Result |
|---|---|---|---|
| HLESource | 58.7% | 56% | GPT-5.4 Pro leads |
| FrontierScienceSource | 36.7% | — | Not comparable |
| FrontierScience ResearchSource | 36.7% | — | Not comparable |
| HLE w/o toolsSource | 42.7% | 43.5% | Kimi K3 leads |
| GPQASource | — | 93.5% | Not comparable |
| GPQA-DSource | — | 93.5% | Not comparable |
| Artificial Analysis Intelligence IndexSource | — | 57.1% | Not comparable |
| AA-GPQA DiamondSource | — | 93.5% | Not comparable |
| AA-HLESource | — | 44.3% | Not comparable |
| AA-Omniscience IndexSource | — | 18.4% | Not comparable |
| AA-Omniscience AccuracySource | — | 46.0% | Not comparable |
| AA-Omniscience Hallucination RateSource | — | 50.9% | Not comparable |
Math4 benchmarks
MultimodalGPT-5.4 Pro wins15 benchmarks
| Benchmark | GPT-5.4 Pro | Kimi K3 | Result |
|---|---|---|---|
| MMMU-ProSource | 94% | 81.6% | GPT-5.4 Pro leads |
| OfficeQA ProSource | — | 63.3% | Not comparable |
| MMMU-Pro w/ PythonSource | — | 83.4% | Not comparable |
| CharXiv w/o toolsSource | — | 84.8% | Not comparable |
| CharXivSource | — | 91.3% | Not comparable |
| MathVisionSource | — | 94.3% | Not comparable |
| MathVision w/ PythonSource | — | 97.8% | Not comparable |
| BabyVision w/ PythonSource | — | 85.7% | Not comparable |
| ZeroBenchSource | — | 23.0% | Not comparable |
| ZeroBench w/ PythonSource | — | 41.0% | Not comparable |
| WorldVQA ForceAnswerSource | — | 51.0% | Not comparable |
| OmniDocBenchSource | — | 91.1% | Not comparable |
| PerceptionBenchSource | — | 58.5% | Not comparable |
| AA-MMMU-ProSource | — | 80.5% | Not comparable |
| Design Arena WebsiteSource | — | 1386 | Not comparable |
Frequently Asked Questions (4)
Which is better, GPT-5.4 Pro or Kimi K3?
Kimi K3 is ahead on BenchLM's BenchAlign leaderboard, 80.96 to 60.89. The biggest single separator in this matchup is MMMU-Pro, where the scores are 94% and 81.6%.
Which is better for knowledge tasks, GPT-5.4 Pro or Kimi K3?
Kimi K3 has the edge for knowledge tasks in this comparison, averaging 61 versus 58.7. Inside this category, HLE is the benchmark that creates the most daylight between them.
Which is better for agentic tasks, GPT-5.4 Pro or Kimi K3?
Kimi K3 has the edge for agentic tasks in this comparison, averaging 89.5 versus 89.3. Inside this category, BrowseComp is the benchmark that creates the most daylight between them.
Which is better for multimodal and grounded tasks, GPT-5.4 Pro or Kimi K3?
GPT-5.4 Pro has the edge for multimodal and grounded tasks in this comparison, averaging 94 versus 78.5. Inside this category, MMMU-Pro 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.