Model comparison
DeepSeek V4.1 Flash vs GLM-5
DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 46.1 on the Noometry Index.
Last verified . 24 shared benchmarks.
DeepSeekSummary
- They share 24 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 8 categories and GLM-5 in 1 category; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4.1 Flash leads 50.2 to 27.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 98.3% for DeepSeek V4.1 Flash and 80% for GLM-5.
- DeepSeek V4.1 Flash is cheaper at $0.15 / $0.60 per million input/output tokens, against $1 / $3.20 for GLM-5.
- DeepSeek V4.1 Flash accepts more context: 1M tokens versus 205K.
Side by side
| DeepSeek V4.1 Flash | GLM-5 | |
|---|---|---|
| Provider | DeepSeek | Z.ai (Zhipu) |
| Noometry Index | 52.8 | 46.1 |
| Released | 2026-09-09 | 2026-02-11 |
| Weights | Open | Open |
| Context window | 1M | 205K |
| Max output | 393K | 131K |
| Input $ / M tokens | $0.15 | $1 |
| Output $ / M tokens | $0.60 | $3.20 |
| Results tracked | 37 | 45 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 52.9 (#32), GLM-5: 49.0 (#52)
| Benchmark | DeepSeek V4.1 Flash | GLM-5 |
|---|---|---|
| LMArena WebDev | 1619 | 1434 |
| LMArena Coding | 1506 | 1461 |
| ALE-Bench | 1,092 | 765.62 |
| SWE-bench Verified | — | 72.1% |
| SWE-bench Verified (bash only) | — | 72.8% |
| SWE-bench Multilingual | — | 69.7% |
| SciCode | 51.9% | — |
| WeirdML | — | 48.2% |
Agentic & Tool Use Too close to call
DeepSeek V4.1 Flash: 31.2 (#69), GLM-5: 31.1 (#71)
| Benchmark | DeepSeek V4.1 Flash | GLM-5 |
|---|---|---|
| Terminal-Bench | — | 52.4% |
| APEX-Agents | 39.5% | — |
| τ²-bench Airline | — | 82.5% |
| τ²-bench Banking | — | 9.8% |
| τ²-bench Retail | — | 73.7% |
| τ²-bench Telecom | — | 86.8% |
| GDP.pdf | 19.8% | — |
| Vending-Bench 2 | — | 4,432 |
Reasoning DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 50.2 (#36), GLM-5: 27.6 (#116)
| Benchmark | DeepSeek V4.1 Flash | GLM-5 |
|---|---|---|
| NYT Connections (extended) | 89.6% | 74.8% |
| LMArena Hard Prompts | 1483 | 1452 |
| Epoch Capabilities Index | 154.9 | 145.83 |
| ARC-AGI-2 | — | 4.9% |
| SimpleBench | — | 53.2% |
| Kagi LLM Benchmark | — | 75% |
| ARC-AGI-1 | — | 44.7% |
| CritPt | 14.3% | — |
| Chess Puzzles | — | 10% |
| Mystery Game Puzzles | 43% | — |
| DTBench | 89.9% | — |
| LMCA | 47% | — |
| Surface Evolver Bench | 46.3% | — |
| ForecastBench | — | 61 |
Math DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 66.7 (#25), GLM-5: 46.4 (#71)
| Benchmark | DeepSeek V4.1 Flash | GLM-5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 98.3% | 80% |
| LMArena Math | 1477 | 1440 |
| FrontierMath (Tiers 1-3) | 67.4% | — |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | — | 65.7% |
| ProofBench | 54% | — |
| FrontierMath (Feb 2025 set) | — | 16.4% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 57.9 (#38), GLM-5: 52.3 (#64)
| Benchmark | DeepSeek V4.1 Flash | GLM-5 |
|---|---|---|
| GPQA Diamond | 89.8% | 87.8% |
| LMArena Expert | 1506 | 1454 |
| Vectara Hallucination Rate | — | 10.1% |
Multimodal Not comparable
DeepSeek V4.1 Flash: 39.1 (#61), GLM-5: —
| Benchmark | DeepSeek V4.1 Flash | GLM-5 |
|---|---|---|
| LMArena Vision | 1277 | — |
| Furniture Assembly | 34.2% | — |
Multilingual DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 55.0 (#35), GLM-5: 53.7 (#58)
| Benchmark | DeepSeek V4.1 Flash | GLM-5 |
|---|---|---|
| LMArena Non-English | 1448 | 1430 |
| LMArena Chinese | 1497 | 1511 |
| LMArena French | 1452 | 1455 |
| LMArena German | 1484 | 1445 |
| LMArena Japanese | 1412 | 1416 |
| LMArena Korean | 1452 | 1423 |
| LMArena Russian | 1471 | 1436 |
| LMArena Spanish | 1459 | 1454 |
Instruction Following DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 77.3 (#26), GLM-5: 75.2 (#67)
| Benchmark | DeepSeek V4.1 Flash | GLM-5 |
|---|---|---|
| LMArena Instruction Following | 1474 | 1428 |
Long Context Too close to call
DeepSeek V4.1 Flash: 45.2 (#47), GLM-5: 44.7 (#60)
| Benchmark | DeepSeek V4.1 Flash | GLM-5 |
|---|---|---|
| LMArena Longer Query | 1475 | 1446 |
| CL-bench | — | 18.7% |
Writing & Preference Too close to call
DeepSeek V4.1 Flash: 65.4 (#48), GLM-5: 66.0 (#38)
| Benchmark | DeepSeek V4.1 Flash | GLM-5 |
|---|---|---|
| LMArena Text | 1462 | 1446 |
| LMArena Creative Writing | 1435 | 1439 |
| EQ-Bench Creative Writing | 1540 | 1601 |
| LMArena Multi-Turn | 1457 | 1456 |
Frequently asked questions
Is DeepSeek V4.1 Flash better than GLM-5?
DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 46.1 on the Noometry Index.
Which is cheaper, DeepSeek V4.1 Flash or GLM-5?
DeepSeek V4.1 Flash is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; GLM-5 lists at $1 and $3.20.
Is DeepSeek V4.1 Flash or GLM-5 better for coding?
DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.9 versus 49.0 in the Noometry coding category.
Which has the bigger context window?
DeepSeek V4.1 Flash does, with 1M tokens against 205K.
How many benchmarks do DeepSeek V4.1 Flash and GLM-5 share?
24 benchmarks have published results for both models. DeepSeek V4.1 Flash has 37 scored results on Noometry and GLM-5 has 45.