Model comparison
Kimi K3 vs Mercury 2.5
Kimi K3 is the stronger model overall, scoring 59.5 to 33.5 on the Noometry Index. Mercury 2.5 costs 89× less per token, which makes it the better buy when Kimi K3's lead doesn't matter for your workload.
Last verified . 4 shared benchmarks.
Summary
- They share 4 benchmarks with published results for both. Kimi K3 scores higher in 3 categories and Mercury 2.5 in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K3 leads 74.2 to 23.3.
- The biggest single-benchmark swing is ProofBench: 87% for Kimi K3 and 3% for Mercury 2.5.
- Mercury 2.5 is cheaper at $0.04 / $0.15 per million input/output tokens, against $3 / $15 for Kimi K3.
- Kimi K3 accepts more context: 1.05M tokens versus 260K.
- Kimi K3 has downloadable open weights; the other is API-only.
Side by side
| Kimi K3 | Mercury 2.5 | |
|---|---|---|
| Provider | Moonshot AI | Inception |
| Noometry Index | 59.5 | 33.5 |
| Released | 2026-07-16 | 2026-09-08 |
| Weights | Open | Proprietary |
| Context window | 1.05M | 260K |
| Max output | 1.05M | 66K |
| Input $ / M tokens | $3 | $0.04 |
| Output $ / M tokens | $15 | $0.15 |
| Results tracked | 53 | 4 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K3 leads
Kimi K3: 61.0 (#10), Mercury 2.5: 39.5 (#156)
| Benchmark | Kimi K3 | Mercury 2.5 |
|---|---|---|
| SciCode | 59.5% | 38.5% |
| ALE-Bench | 1,524 | 301.65 |
| DeepSWE | 68.5% | — |
| FrontierCode | 44.2% | — |
| LMArena WebDev | 1654 | — |
| FrontierSWE | 25.9% | — |
| WeirdML | 82.6% | — |
| LMArena Coding | 1508 | — |
Agentic & Tool Use Not comparable
Kimi K3: 41.8 (#20), Mercury 2.5: —
| Benchmark | Kimi K3 | Mercury 2.5 |
|---|---|---|
| APEX-Agents | 50.6% | — |
| τ²-bench Banking | 37.1% | — |
| PostTrainBench | 32% | — |
| GBAEval | 48.3% | — |
| GDP.pdf | 19% | — |
| Vending-Bench 2 | 5,165 | — |
Reasoning Kimi K3 leads
Kimi K3: 63.0 (#17), Mercury 2.5: 22.4 (#193)
| Benchmark | Kimi K3 | Mercury 2.5 |
|---|---|---|
| CritPt | 23.4% | 0% |
| ARC-AGI-2 | 60.4% | — |
| SimpleBench | 60.7% | — |
| NYT Connections (extended) | 93.6% | — |
| ARC-AGI-1 | 94.5% | — |
| Chess Puzzles | 39% | — |
| LMArena Hard Prompts | 1496 | — |
| Mystery Game Puzzles | 26% | — |
| DTBench | 91.2% | — |
| LMCA | 52.7% | — |
| Surface Evolver Bench | 95% | — |
| Epoch Capabilities Index | 157.45 | — |
| ForecastBench | 61.1 | — |
Math Kimi K3 leads
Kimi K3: 74.2 (#16), Mercury 2.5: 23.3 (#272)
| Benchmark | Kimi K3 | Mercury 2.5 |
|---|---|---|
| ProofBench | 87% | 3% |
| FrontierMath (Tiers 1-3) | 72.2% | — |
| FrontierMath Tier 4 | 39% | — |
| MathArena Final-Answer Competitions | 87.8% | — |
| OTIS Mock AIME 2024-2025 | 97.2% | — |
| LMArena Math | 1491 | — |
Knowledge Not comparable
Kimi K3: 63.2 (#21), Mercury 2.5: —
| Benchmark | Kimi K3 | Mercury 2.5 |
|---|---|---|
| GPQA Diamond | 93.1% | — |
| SimpleQA Verified | 50.6% | — |
| LMArena Expert | 1521 | — |
Multimodal Not comparable
Kimi K3: 37.8 (#70), Mercury 2.5: —
| Benchmark | Kimi K3 | Mercury 2.5 |
|---|---|---|
| Blueprint-Bench 2 | 29.5% | — |
| Furniture Assembly | 34.2% | — |
Multilingual Not comparable
Kimi K3: 56.3 (#21), Mercury 2.5: —
| Benchmark | Kimi K3 | Mercury 2.5 |
|---|---|---|
| LMArena Non-English | 1466 | — |
| LMArena Chinese | 1529 | — |
| LMArena French | 1491 | — |
| LMArena German | 1488 | — |
| LMArena Japanese | 1487 | — |
| LMArena Korean | 1458 | — |
| LMArena Russian | 1482 | — |
| LMArena Spanish | 1472 | — |
Instruction Following Not comparable
Kimi K3: 77.7 (#14), Mercury 2.5: —
| Benchmark | Kimi K3 | Mercury 2.5 |
|---|---|---|
| LMArena Instruction Following | 1483 | — |
Long Context Not comparable
Kimi K3: 45.8 (#29), Mercury 2.5: —
| Benchmark | Kimi K3 | Mercury 2.5 |
|---|---|---|
| LMArena Longer Query | 1494 | — |
Writing & Preference Not comparable
Kimi K3: 76.6 (#4), Mercury 2.5: —
| Benchmark | Kimi K3 | Mercury 2.5 |
|---|---|---|
| LMArena Text | 1476 | — |
| LMArena Creative Writing | 1454 | — |
| EQ-Bench Creative Writing | 2082 | — |
| EQ-Bench 4 | 1339 | — |
| LMArena Multi-Turn | 1488 | — |
Frequently asked questions
Is Kimi K3 better than Mercury 2.5?
Kimi K3 is the stronger model overall, scoring 59.5 to 33.5 on the Noometry Index. Mercury 2.5 costs 89× less per token, which makes it the better buy when Kimi K3's lead doesn't matter for your workload.
Which is cheaper, Kimi K3 or Mercury 2.5?
Mercury 2.5 is cheaper. It lists at $0.04 per million input tokens and $0.15 per million output tokens; Kimi K3 lists at $3 and $15.
Is Kimi K3 or Mercury 2.5 better for coding?
Kimi K3 scores higher on coding benchmarks: 61.0 versus 39.5 in the Noometry coding category.
Which has the bigger context window?
Kimi K3 does, with 1.05M tokens against 260K.
How many benchmarks do Kimi K3 and Mercury 2.5 share?
4 benchmarks have published results for both models. Kimi K3 has 53 scored results on Noometry and Mercury 2.5 has 4.