Model comparison
Kimi K2.5 vs Mistral Medium 3.5 128B
Head-to-head evidence from 19 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: Kimi K2.5 #60 (Supported); Mistral Medium 3.5 128B unranked (Not scored). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. Kimi K2.5 and Mistral Medium 3.5 128B share 19 comparable benchmark results. 1 of 8 categories are comparable. 44 results are unique to Kimi K2.5; 6 to Mistral Medium 3.5 128B.
Updated July 27, 2026- Shared results
- 19
- Kimi K2.5 only
- 44
- Mistral Medium 3.5 128B only
- 6
- Comparable categories
- 1 / 8
Treat this as a split decision. Kimi K2.5 makes more sense if you want the cheaper token bill or you would rather avoid the extra latency and token burn of a reasoning model; Mistral Medium 3.5 128B is the better fit if coding is the priority or you want the stronger reasoning-first profile.
Confidence note. This is a partial-evidence comparison with 19 shared benchmark results across 6 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
Kimi K2.5 and Mistral Medium 3.5 128B finish on the same BenchAlign overall score, so this is less about a single winner and more about where the edge shows up. The BenchAlign headline says tie; the benchmark table is where the real choice happens.
Mistral Medium 3.5 128B is also the more expensive model on tokens at $1.50 input / $7.50 output per 1M tokens, versus $0.60 input / $3.00 output per 1M tokens for Kimi K2.5. That is roughly 2.5x on output cost alone. Mistral Medium 3.5 128B is the reasoning model in the pair, while Kimi K2.5 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.
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 K2.5 | Δ | Mistral Medium 3.5 128B |
|---|---|---|---|
| Coding | Kimi K2.559.4 | Margin→ 18.2 | Mistral Medium 3.5 128B77.6 |
| Agentic | Kimi K2.555.0 | MarginNo overlap | Mistral Medium 3.5 128BNot measured |
| Reasoning | Kimi K2.561.0 | MarginNo overlap | Mistral Medium 3.5 128BNot measured |
| Knowledge | Kimi K2.556.9 | MarginNo overlap | Mistral Medium 3.5 128BNot measured |
| Math | Kimi K2.560.6 | MarginNo overlap | Mistral Medium 3.5 128BNot measured |
| Multilingual | Kimi K2.582.3 | MarginNo overlap | Mistral Medium 3.5 128BNot measured |
| Multimodal | Kimi K2.578.5 | MarginNo overlap | Mistral Medium 3.5 128BNot measured |
| Inst. Following | Kimi K2.593.9 | MarginNo overlap | Mistral Medium 3.5 128BNot measured |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
SWE-bench Verified
CodingA 76.8%B 77.6%Winner: Mistral Medium 3.5 128BΔ 0.8SWE-bench Verified: Kimi K2.5 scored 76.8%; Mistral Medium 3.5 128B scored 77.6%. Mistral Medium 3.5 128B wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | Kimi K2.5 | Mistral Medium 3.5 128B | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Kimi K2.5$0.6 input / $3 output | Mistral Medium 3.5 128B$1.5 input / $7.5 output | Kimi K2.5 has the lower combined listed price. |
| Generation speedtokens per second | Kimi K2.545 tok/s | Mistral Medium 3.5 128BNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | Kimi K2.52.38 s | Mistral Medium 3.5 128BNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | Kimi K2.5256K | Mistral Medium 3.5 128B256K | Listed context windows are equal. |
Benchmark Deep Dive
Agentic24 benchmarks
| Benchmark | Kimi K2.5 | Mistral Medium 3.5 128B | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 50.8% | — | Not comparable |
| BrowseCompSource | 60.6% | — | Not comparable |
| Claw-EvalSource | 52.3% | — | Not comparable |
| QwenClawBenchSource | 54.3% | — | Not comparable |
| τ³-bench resultsSource | 65.7% | 91.4% | Mistral Medium 3.5 128B leads |
| DeepSearchQASource | 77.1% | — | Not comparable |
| DeepPlanningSource | 14.4% | — | Not comparable |
| ToolathlonSource | 27.8% | — | Not comparable |
| MCP AtlasSource | 29.5% | — | Not comparable |
| MCP-TasksSource | 59.1% | — | Not comparable |
| WideResearchSource | 72.7% | — | Not comparable |
| τ²-bench resultsSource | 95.9% | 94.2% | Kimi K2.5 leads |
| APEX-Agents-AASource | 11.5% | — | Not comparable |
| Gert LabsSource | 45.88% | 39.10% | Kimi K2.5 leads |
| ResearchClawBenchSource | 14.0% | — | Not comparable |
| JobBenchSource | 8.7% | — | Not comparable |
| AA Agentic IndexSource | 21.7% | 19.0% | Kimi K2.5 leads |
| GDPval-AASource | 25.1% | 21.6% | Kimi K2.5 leads |
| GDPval-AASource | 1003 | 933 | Kimi K2.5 leads |
| AA EnterpriseOps-GymSource | — | 33.7% | Not comparable |
| AA Harvey LABSource | — | 69.1% | Not comparable |
| terminalBenchHardSource | — | 33.3% | Not comparable |
| AA BriefcaseSource | — | 516 | Not comparable |
| AA Tau3 BankingSource | — | 14.4% | Not comparable |
CodingMistral Medium 3.5 128B wins10 benchmarks
| Benchmark | Kimi K2.5 | Mistral Medium 3.5 128B | Result |
|---|---|---|---|
| SWE-bench VerifiedSource | 76.8% | 77.6% | Mistral Medium 3.5 128B leads |
| SWE-bench Verified*Source | 70.8% | — | Not comparable |
| LiveCodeBench v6Source | 85.0% | — | Not comparable |
| SWE-bench ProSource | 50.7% | — | Not comparable |
| SWE MultilingualSource | 73% | — | Not comparable |
| SWE-RebenchSource | 58.5% | — | Not comparable |
| React Native EvalsSource | 77.2% | — | Not comparable |
| SciCodeSource | 48.7% | — | Not comparable |
| AA-SciCodeSource | 49.0% | 39.6% | Kimi K2.5 leads |
| AA Coding IndexSource | 46.8% | 46.9% | Mistral Medium 3.5 128B leads |
Reasoning3 benchmarks
Knowledge13 benchmarks
| Benchmark | Kimi K2.5 | Mistral Medium 3.5 128B | Result |
|---|---|---|---|
| GPQASource | 87.6% | — | Not comparable |
| GPQA-DSource | 87.6% | — | Not comparable |
| SuperGPQASource | 69.2% | — | Not comparable |
| MMLU-ProSource | 87.1% | — | Not comparable |
| MMLU-Pro (Arcee)Source | 87.1% | — | Not comparable |
| HLESource | 30.1% | — | Not comparable |
| Artificial Analysis Intelligence IndexSource | 35.4% | 29.9% | Kimi K2.5 leads |
| AA-GPQA DiamondSource | 87.9% | 74.8% | Kimi K2.5 leads |
| AA-HLESource | 29.4% | 12.8% | Kimi K2.5 leads |
| AA-Omniscience IndexSource | -8.1% | -36.3% | Kimi K2.5 leads |
| AA-Omniscience AccuracySource | 34.3% | 25.1% | Kimi K2.5 leads |
| AA-Omniscience Hallucination RateSource | 64.6% | 82.0% | Kimi K2.5 leads |
| AA Openness IndexSource | — | 33.3% | Not comparable |
Math9 benchmarks
| Benchmark | Kimi K2.5 | Mistral Medium 3.5 128B | Result |
|---|---|---|---|
| AIME 2025Source | 96.1% | — | Not comparable |
| AIME26Source | 95.8% | — | Not comparable |
| AIME25 (Arcee)Source | 96.3% | — | Not comparable |
| HMMT Feb 2025Source | 95.4% | — | Not comparable |
| HMMT Nov 2025Source | 91.1% | — | Not comparable |
| HMMT Feb 2026Source | 87.1% | — | Not comparable |
| MMAnswerBenchSource | 81.8% | — | Not comparable |
| FrontierMath v2 (Tiers 1-3)Source | 27.900% | — | Not comparable |
| FrontierMath v2 (Tier 4)Source | 4.200% | — | Not comparable |
Multilingual2 benchmarks
Multimodal6 benchmarks
Frequently Asked Questions (2)
Which is better, Kimi K2.5 or Mistral Medium 3.5 128B?
Kimi K2.5 and Mistral Medium 3.5 128B are tied on the BenchAlign overall score, so the right pick depends on which category matters most for your use case.
Which is better for coding, Kimi K2.5 or Mistral Medium 3.5 128B?
Mistral Medium 3.5 128B has the edge for coding in this comparison, averaging 77.6 versus 59.4. Inside this category, AA-SciCode is the benchmark that creates the most daylight between them.
Self-host vs API cost
Estimates at 50,000 req/day · 1000 tokens/req average.
Related Comparisons
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
One email each week. Unsubscribe anytime.