Model comparison
GLM-5.3-Flash vs Mercury 2.5
GLM-5.3-Flash is the stronger model overall, scoring 51.8 to 33.5 on the Noometry Index. Mercury 2.5 costs 3.5× less per token, which makes it the better buy when GLM-5.3-Flash's lead doesn't matter for your workload.
Last verified . 4 shared benchmarks.
Summary
- They share 4 benchmarks with published results for both. GLM-5.3-Flash 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 GLM-5.3-Flash leads 53.3 to 23.3.
- The biggest single-benchmark swing is ProofBench: 21% for GLM-5.3-Flash and 3% for Mercury 2.5.
- Mercury 2.5 is cheaper at $0.04 / $0.15 per million input/output tokens, against $0.15 / $0.50 for GLM-5.3-Flash.
- GLM-5.3-Flash accepts more context: 1M tokens versus 260K.
- GLM-5.3-Flash has downloadable open weights; the other is API-only.
Side by side
| GLM-5.3-Flash | Mercury 2.5 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Inception |
| Noometry Index | 51.8 | 33.5 |
| Released | 2026-08-20 | 2026-09-08 |
| Weights | Open | Proprietary |
| Context window | 1M | 260K |
| Max output | 131K | 66K |
| Input $ / M tokens | $0.15 | $0.04 |
| Output $ / M tokens | $0.50 | $0.15 |
| Results tracked | 40 | 4 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.3-Flash leads
GLM-5.3-Flash: 53.1 (#31), Mercury 2.5: 39.5 (#156)
| Benchmark | GLM-5.3-Flash | Mercury 2.5 |
|---|---|---|
| SciCode | 51.6% | 38.5% |
| ALE-Bench | 303.55 | 301.65 |
| DeepSWE | 63.4% | — |
| FrontierCode | 31.8% | — |
| CursorBench | 36.8% | — |
| LMArena WebDev | 1609 | — |
| FrontierSWE | 18.1% | — |
| LMArena Coding | 1508 | — |
Agentic & Tool Use Not comparable
GLM-5.3-Flash: 34.2 (#47), Mercury 2.5: —
| Benchmark | GLM-5.3-Flash | Mercury 2.5 |
|---|---|---|
| APEX-Agents | 52.8% | — |
| GDP.pdf | 14% | — |
Reasoning GLM-5.3-Flash leads
GLM-5.3-Flash: 48.0 (#42), Mercury 2.5: 22.4 (#193)
| Benchmark | GLM-5.3-Flash | Mercury 2.5 |
|---|---|---|
| CritPt | 15.4% | 0% |
| ARC-AGI-2 | 65.8% | — |
| ARC-AGI-1 | 91% | — |
| Chess Puzzles | 14% | — |
| LMArena Hard Prompts | 1491 | — |
| Mystery Game Puzzles | 8% | — |
| Surface Evolver Bench | 52.5% | — |
| Bench to the Future 3 | 0.15 | — |
| Epoch Capabilities Index | 151.88 | — |
Math GLM-5.3-Flash leads
GLM-5.3-Flash: 53.3 (#47), Mercury 2.5: 23.3 (#272)
| Benchmark | GLM-5.3-Flash | Mercury 2.5 |
|---|---|---|
| ProofBench | 21% | 3% |
| FrontierMath (Tiers 1-3) | 55.8% | — |
| FrontierMath Tier 4 | 17.1% | — |
| OTIS Mock AIME 2024-2025 | 93.9% | — |
| LMArena Math | 1500 | — |
Knowledge Not comparable
GLM-5.3-Flash: 58.4 (#36), Mercury 2.5: —
| Benchmark | GLM-5.3-Flash | Mercury 2.5 |
|---|---|---|
| GPQA Diamond | 90.2% | — |
| LMArena Expert | 1513 | — |
Multimodal Not comparable
GLM-5.3-Flash: 42.8 (#27), Mercury 2.5: —
| Benchmark | GLM-5.3-Flash | Mercury 2.5 |
|---|---|---|
| LMArena Vision | 1296 | — |
Multilingual Not comparable
GLM-5.3-Flash: 56.0 (#25), Mercury 2.5: —
| Benchmark | GLM-5.3-Flash | Mercury 2.5 |
|---|---|---|
| LMArena Non-English | 1462 | — |
| LMArena Chinese | 1527 | — |
| LMArena French | 1496 | — |
| LMArena German | 1470 | — |
| LMArena Japanese | 1429 | — |
| LMArena Korean | 1446 | — |
| LMArena Russian | 1469 | — |
| LMArena Spanish | 1471 | — |
Instruction Following Not comparable
GLM-5.3-Flash: 77.5 (#20), Mercury 2.5: —
| Benchmark | GLM-5.3-Flash | Mercury 2.5 |
|---|---|---|
| LMArena Instruction Following | 1478 | — |
Long Context Not comparable
GLM-5.3-Flash: 45.4 (#39), Mercury 2.5: —
| Benchmark | GLM-5.3-Flash | Mercury 2.5 |
|---|---|---|
| LMArena Longer Query | 1482 | — |
Writing & Preference Not comparable
GLM-5.3-Flash: 65.3 (#50), Mercury 2.5: —
| Benchmark | GLM-5.3-Flash | Mercury 2.5 |
|---|---|---|
| LMArena Text | 1471 | — |
| LMArena Creative Writing | 1442 | — |
| LMArena Multi-Turn | 1467 | — |
Frequently asked questions
Is GLM-5.3-Flash better than Mercury 2.5?
GLM-5.3-Flash is the stronger model overall, scoring 51.8 to 33.5 on the Noometry Index. Mercury 2.5 costs 3.5× less per token, which makes it the better buy when GLM-5.3-Flash's lead doesn't matter for your workload.
Which is cheaper, GLM-5.3-Flash 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; GLM-5.3-Flash lists at $0.15 and $0.50.
Is GLM-5.3-Flash or Mercury 2.5 better for coding?
GLM-5.3-Flash scores higher on coding benchmarks: 53.1 versus 39.5 in the Noometry coding category.
Which has the bigger context window?
GLM-5.3-Flash does, with 1M tokens against 260K.
How many benchmarks do GLM-5.3-Flash and Mercury 2.5 share?
4 benchmarks have published results for both models. GLM-5.3-Flash has 40 scored results on Noometry and Mercury 2.5 has 4.