# GPT-5.4 vs Kimi K2.5

> Side-by-side benchmark comparison for GPT-5.4 and Kimi K2.5 across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/gpt-5-4-vs-kimi-k2-5
- Last updated: October 17, 2026

- Shared sourced benchmarks: 19
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Pick GPT-5.4 if you want the stronger benchmark profile. Kimi K2.5 only makes more sense when its price, context window, or workload-specific category wins matter more than the overall score.

## Summary

- GPT-5.4 leads overall 66.7 to 53.05.
- The clearest category separation is in knowledge, where the averages are 69.1 for GPT-5.4 and 51.4 for Kimi K2.5.
- The biggest single benchmark swing is MCP Atlas in Agentic, with scores of 70.6% and 29.5%.
- Kimi K2.5 is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.
- GPT-5.4 also has the larger context window at 1.05M.

## Model Snapshot

| Property | GPT-5.4 | Kimi K2.5 |
|----------|----------|----------|
| Creator | OpenAI | Moonshot AI |
| Type | Proprietary | Open Weight |
| Reasoning | Reasoning | Non-Reasoning |
| Context | 1.05M | 256K |
| Overall Score | 66.7 | 53.05 |
| Benchmarks Covered | 42 | 68 |
| Pricing (input/output) | $2.50 / $15.00 | $0.60 / $3.00 |

## Category Breakdown

### Agentic

- Winner: Directional only
- GPT-5.4 public-lane score: 52.1 (Supported · #44/128)
- Kimi K2.5 public-lane score: 40.7 (Estimated · #66/128)

| Benchmark | GPT-5.4 | Kimi K2.5 | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 75.1% | 50.8% | GPT-5.4 |
| CyberGym | 79.0% | Coming soon | Coming soon |
| BrowseComp | 82.7% | 60.6% | GPT-5.4 |
| OSWorld-Verified | 75% | 63.3% | GPT-5.4 |
| MCP Atlas | 70.6% | 29.5% | GPT-5.4 |
| Toolathlon | 54.6% | 27.8% | GPT-5.4 |
| τ²-bench results | 98.9% | Coming soon | Coming soon |
| Claw-Eval | 60.3% | 52.3% | GPT-5.4 |
| DeepSearchQA | 73.6% | 77.1% | Kimi K2.5 |
| Gert Labs | 64.89% | 45.88% | GPT-5.4 |
| ResearchClawBench | 15.3% | 14.0% | GPT-5.4 |
| JobBench | 38.9% | 8.7% | GPT-5.4 |
| ExploitGym | 6.0% | Coming soon | Coming soon |
| ApprenticeBench | 11% | Coming soon | Coming soon |
| MazeBench | 0% | Coming soon | Coming soon |
| QwenClawBench | Coming soon | 54.3% | Coming soon |
| τ³-bench results | Coming soon | 65.7% | Coming soon |
| DeepPlanning | Coming soon | 14.4% | Coming soon |
| MCP-Tasks | Coming soon | 59.1% | Coming soon |
| WideResearch | Coming soon | 72.7% | Coming soon |
| BFCL v4 | Coming soon | 68.3% | Coming soon |

### Coding

- Winner: Directional only
- GPT-5.4 public-lane score: 47.7 (Supported · #48/150)
- Kimi K2.5 public-lane score: 38.5 (Estimated · #68/150)

| Benchmark | GPT-5.4 | Kimi K2.5 | Winner |
|-----------|-----------|-----------|--------|
| LiveCodeBench Pro | 87.5% | Coming soon | Coming soon |
| SWE-bench Pro | 57.7% | 50.7% | GPT-5.4 |
| React Native Evals | 85.3% | 77.2% | GPT-5.4 |
| Terminal-Bench 2.0 | 75.1% | 50.8% | GPT-5.4 |
| Vibe Code Bench | 67.42% | Coming soon | Coming soon |
| PostTrainBench v1.1 | 19.0% | Coming soon | Coming soon |
| SWE-bench Verified | Coming soon | 76.8% | Coming soon |
| SWE-bench Verified* | Coming soon | 70.8% | Coming soon |
| LiveCodeBench v6 | Coming soon | 85.0% | Coming soon |
| SWE Multilingual | Coming soon | 73% | Coming soon |
| SWE-Rebench | Coming soon | 58.5% | Coming soon |
| NL2Repo | Coming soon | 32% | Coming soon |
| SciCode | Coming soon | 48.7% | Coming soon |

### Reasoning

- Winner: Not comparable
- GPT-5.4 public-lane score: 64.2 (#23/28)
- Kimi K2.5 public-lane score: 72.2 (Unranked · 3 rankable rows)

| Benchmark | GPT-5.4 | Kimi K2.5 | Winner |
|-----------|-----------|-----------|--------|
| ARC-AGI-2 | 74.0% | Coming soon | Coming soon |
| ARC-AGI-3 | 0.2% | Coming soon | Coming soon |
| ARC-AGI-1 | 93.67% | Coming soon | Coming soon |
| LongBench v2 | Coming soon | 61% | Coming soon |

### Multimodal & Grounded

- Winner: Directional only
- GPT-5.4 public-lane score: 73.1 (#30/54)
- Kimi K2.5 public-lane score: 70.4 (#32/54)

| Benchmark | GPT-5.4 | Kimi K2.5 | Winner |
|-----------|-----------|-----------|--------|
| MMMU-Pro | 81.2% | 78.5% | GPT-5.4 |
| OfficeQA Pro | 53.2% | Coming soon | Coming soon |
| MMMU-Pro w/ Python | 82.1% | Coming soon | Coming soon |
| CharXiv | 82.8% | 77.5% | GPT-5.4 |
| ERQA | 65.4% | Coming soon | Coming soon |
| SimpleVQA | 61.1% | 71.2% | Kimi K2.5 |
| ScreenSpot Pro | 85.4% | Coming soon | Coming soon |
| ZeroBench | 41.0% | Coming soon | Coming soon |
| MedXpertQA (MM) | 77.1% | Coming soon | Coming soon |
| MMMU | Coming soon | 84.3% | Coming soon |
| RealWorldQA | Coming soon | 81.0% | Coming soon |
| OmniDocBench 1.5 | Coming soon | 88.8% | Coming soon |
| Video-MME | Coming soon | 87.4% | Coming soon |
| Video-MME (with subtitle) | Coming soon | 87.4% | Coming soon |
| Video-MME (w/o subtitle) | Coming soon | 83.2% | Coming soon |
| MathVision | Coming soon | 84.2% | Coming soon |
| We-Math | Coming soon | 84.7% | Coming soon |
| DynaMath | Coming soon | 84.4% | Coming soon |
| MMLongBench-Doc | Coming soon | 58.5% | Coming soon |
| CC-OCR | Coming soon | 79.7% | Coming soon |
| AI2D_TEST | Coming soon | 90.8% | Coming soon |
| CountBench | Coming soon | 94.1% | Coming soon |
| RefCOCO (avg) | Coming soon | 87.8% | Coming soon |
| MMVU | Coming soon | 80.4% | Coming soon |
| VideoMMMU | Coming soon | 86.6% | Coming soon |
| MLVU (M-Avg) | Coming soon | 85.0% | Coming soon |

### Knowledge

- Winner: Directional only
- GPT-5.4 public-lane score: 69.1 (Supported · #20/184)
- Kimi K2.5 public-lane score: 51.4 (Estimated · #75/184)

| Benchmark | GPT-5.4 | Kimi K2.5 | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 92.8% | 87.6% | GPT-5.4 |
| HLE | 52.1% | 30.1% | GPT-5.4 |
| HLE w/o tools | 39.8% | Coming soon | Coming soon |
| GPQA-D | 92.8% | 87.6% | GPT-5.4 |
| HealthBench Hard | 40.1% | Coming soon | Coming soon |
| MedXpertQA (Text) | 59.6% | Coming soon | Coming soon |
| HealthBench Professional | 48.1% | Coming soon | Coming soon |
| SuperGPQA | Coming soon | 69.2% | Coming soon |
| MMLU-Pro | Coming soon | 87.1% | Coming soon |
| MMLU-Pro (Arcee) | Coming soon | 87.1% | Coming soon |
| MMLU-Redux | Coming soon | 94.5% | Coming soon |
| C-Eval | Coming soon | 94% | Coming soon |

### Multilingual

- Winner: Not comparable
- GPT-5.4 public-lane score: Coming soon
- Kimi K2.5 public-lane score: 87.3 (#8/17)

| Benchmark | GPT-5.4 | Kimi K2.5 | Winner |
|-----------|-----------|-----------|--------|
| MMLU-ProX | Coming soon | 82.3% | Coming soon |
| NOVA-63 | Coming soon | 56.0% | Coming soon |
| INCLUDE | Coming soon | 83.3% | Coming soon |
| PolyMath | Coming soon | 43.1% | Coming soon |
| MAXIFE | Coming soon | 72.8% | Coming soon |

### Instruction Following

- Winner: Directional only
- GPT-5.4 public-lane score: 90.7 (#23/148)
- Kimi K2.5 public-lane score: 85.8 (#48/148)

| Benchmark | GPT-5.4 | Kimi K2.5 | Winner |
|-----------|-----------|-----------|--------|
| IFEval | Coming soon | 93.9% | Coming soon |

### Mathematics

- Winner: Not comparable
- GPT-5.4 public-lane score: 82 (Unranked · 2 rankable rows)
- Kimi K2.5 public-lane score: 83.3 (Unranked · 7 rankable rows)

| Benchmark | GPT-5.4 | Kimi K2.5 | Winner |
|-----------|-----------|-----------|--------|
| FrontierMath v2 (Tiers 1-3) | 78.596% | Coming soon | Coming soon |
| FrontierMath v2 (Tier 4) | 49.000% | Coming soon | Coming soon |
| AIME 2025 | Coming soon | 96.1% | Coming soon |
| AIME26 | Coming soon | 95.8% | Coming soon |
| AIME25 (Arcee) | Coming soon | 96.3% | Coming soon |
| HMMT Feb 2025 | Coming soon | 95.4% | Coming soon |
| HMMT Nov 2025 | Coming soon | 91.1% | Coming soon |
| HMMT Feb 2026 | Coming soon | 87.1% | Coming soon |
| MMAnswerBench | Coming soon | 81.8% | Coming soon |

## FAQ

### Which is better overall, GPT-5.4 or Kimi K2.5?

GPT-5.4 is ahead overall on BenchLM right now.

### Where is the biggest gap between GPT-5.4 and Kimi K2.5?

The widest category gap is in knowledge, where the averages are 69.1 for GPT-5.4 and 51.4 for Kimi K2.5.

### How many benchmarks does GPT-5.4 cover on BenchLM?

GPT-5.4 currently has 42 sourced benchmark scores on BenchLM.

### How many benchmarks does Kimi K2.5 cover on BenchLM?

Kimi K2.5 currently has 68 sourced benchmark scores on BenchLM.

## Related Comparisons

- [GPT-5.4 vs GPT-5.4 Pro](/compare/gpt-5-4-vs-gpt-5-4-pro)
- [Kimi K2.5 vs GPT-5.4 Pro](/compare/gpt-5-4-pro-vs-kimi-k2-5)
- [GPT-5.4 vs GPT-5.4 mini](/compare/gpt-5-4-vs-gpt-5-4-mini)
- [Kimi K2.5 vs GPT-5.4 mini](/compare/gpt-5-4-mini-vs-kimi-k2-5)

## Explore More

- [GPT-5.4 profile](/models/gpt-5-4)
- [Kimi K2.5 profile](/models/kimi-k2-5)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)