Model comparison
Kimi K3 vs Kimi K2.7 Code
Head-to-head evidence from 18 shared benchmark results across 5 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: Kimi K3 #4 (Supported); Kimi K2.7 Code #87 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. Kimi K3 and Kimi K2.7 Code share 18 comparable benchmark results. 0 of 8 categories are comparable. 39 results are unique to Kimi K3; 5 to Kimi K2.7 Code.
Updated July 23, 2026- Shared results
- 18
- Kimi K3 only
- 39
- Kimi K2.7 Code only
- 5
- Comparable categories
- 0 / 8
Benchmark data for Kimi K3 and Kimi K2.7 Code is coming soon on BenchLM.
Confidence note. This is a partial-evidence comparison with 18 shared benchmark results across 5 evidence categories; 0 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
BenchLM has partial data for these models, but not enough overlapping benchmark coverage to produce a fair score-level comparison yet.
Kimi K3 is priced at $3.00 input / $15.00 output per 1M tokens, versus $0.95 input / $4.00 output per 1M tokens for Kimi K2.7 Code. Kimi K3 has the larger context window at 1.05M, compared with 256K for Kimi K2.7 Code.
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 | Kimi K3 | Δ | Kimi K2.7 Code |
|---|---|---|---|
| Agentic | Kimi K389.5 | MarginNo overlap | Kimi K2.7 CodeNot measured |
| Knowledge | Kimi K361.0 | MarginNo overlap | Kimi K2.7 CodeNot measured |
| Multimodal | Kimi K378.5 | MarginNo overlap | Kimi K2.7 CodeNot measured |
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | Kimi K3 | Kimi K2.7 Code | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Kimi K3$3 input / $15 output | Kimi K2.7 Code$0.95 input / $4 output | Kimi K2.7 Code has the lower combined listed price. |
| Generation speedtokens per second | Kimi K3Not available | Kimi K2.7 CodeNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | Kimi K3Not available | Kimi K2.7 CodeNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | Kimi K31.05M | Kimi K2.7 Code256K | Kimi K3 lists the larger context window. |
Benchmark Deep Dive
Agentic24 benchmarks
| Benchmark | Kimi K3 | Kimi K2.7 Code | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 88.3% | — | Not comparable |
| BrowseCompSource | 91.2% | — | Not comparable |
| DeepSearchQASource | 95.0% | — | Not comparable |
| Toolathlon-VerifiedSource | 73.2% | — | Not comparable |
| MCP AtlasSource | 84.2% | 76% | Kimi K3 leads |
| 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% | 29.6% | Kimi K3 leads |
| GDPval-AASource | 59.0% | 34.3% | Kimi K3 leads |
| GDPval-AASource | 1679 | 1187 | Kimi K3 leads |
| 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 |
| Kimi Claw 24/7Source | — | 46.9% | Not comparable |
| MCP Mark VerifiedSource | — | 81.1% | Not comparable |
| τ²-bench resultsSource | — | 90.1% | Not comparable |
Coding10 benchmarks
| Benchmark | Kimi K3 | Kimi K2.7 Code | Result |
|---|---|---|---|
| deepSweSource | 67.5% | — | Not comparable |
| FrontierSWESource | 81.2% | — | Not comparable |
| ProgramBenchSource | 77.8% | 53.6% | Kimi K3 leads |
| Kimi Code Bench v2Source | 72.9% | 62.0% | Kimi K3 leads |
| sweMarathonSource | 42% | — | Not comparable |
| PostTrain BenchSource | 36.6% | — | Not comparable |
| MLS-Bench LiteSource | 48.3% | 35.1% | Kimi K3 leads |
| AA Coding IndexSource | 76.2% | 60.8% | Kimi K3 leads |
| AA-SciCodeSource | 58.7% | 47.5% | Kimi K3 leads |
| cursorBench32Source | — | 49.7% | Not comparable |
Reasoning2 benchmarks
Knowledge10 benchmarks
| Benchmark | Kimi K3 | Kimi K2.7 Code | Result |
|---|---|---|---|
| GPQASource | 93.5% | — | Not comparable |
| GPQA-DSource | 93.5% | — | Not comparable |
| HLESource | 56% | — | Not comparable |
| HLE w/o toolsSource | 43.5% | — | Not comparable |
| Artificial Analysis Intelligence IndexSource | 57.1% | 42.0% | Kimi K3 leads |
| AA-GPQA DiamondSource | 93.5% | 89.6% | Kimi K3 leads |
| AA-HLESource | 44.3% | 32.8% | Kimi K3 leads |
| AA-Omniscience IndexSource | 18.4% | -10.7% | Kimi K3 leads |
| AA-Omniscience AccuracySource | 46.0% | 38.6% | Kimi K3 leads |
| AA-Omniscience Hallucination RateSource | 50.9% | 80.3% | Kimi K3 leads |
Multimodal15 benchmarks
| Benchmark | Kimi K3 | Kimi K2.7 Code | Result |
|---|---|---|---|
| OfficeQA ProSource | 63.3% | — | Not comparable |
| MMMU-ProSource | 81.6% | — | 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 | 1302 | Kimi K3 leads |
Inst. Following1 benchmarks
| Benchmark | Kimi K3 | Kimi K2.7 Code | Result |
|---|---|---|---|
| AA-IFBenchSource | — | 63.1% | Not comparable |
Frequently Asked Questions (3)
Can I compare Kimi K3 and Kimi K2.7 Code on BenchLM yet?
Not fully yet. BenchLM is tracking both models, but the sourced benchmark breakdown for this comparison is still coming soon.
Why does this comparison show “coming soon”?
BenchLM only shows category winners and benchmark-level calls when we have sourced results that can be compared fairly. For these models, the public benchmark coverage is not complete enough yet.
What data is available for Kimi K3 and Kimi K2.7 Code today?
Kimi K3: $3.00 input / $15.00 output per 1M tokens Kimi K2.7 Code: $0.95 input / $4.00 output per 1M tokens Both model pages still include creator, context window, reasoning mode, and other metadata while benchmark coverage fills in.
Self-host vs API cost
Estimates at 50,000 req/day · 1000 tokens/req average.
Related Comparisons
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.