Model comparison
Claude Haiku 4.5 vs GLM-5.3-Flash
GLM-5.3-Flash is the stronger model overall, scoring 49.6 to 39.3 on the Noometry Index.
Last verified . 25 shared benchmarks.
Summary
- They share 25 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 0 categories and GLM-5.3-Flash in 10 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-5.3-Flash leads 58.4 to 37.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 66.7% for Claude Haiku 4.5 and 93.9% for GLM-5.3-Flash.
- GLM-5.3-Flash is cheaper at $0.15 / $0.50 per million input/output tokens, against $1 / $5 for Claude Haiku 4.5.
- GLM-5.3-Flash accepts more context: 1M tokens versus 200K.
- GLM-5.3-Flash has downloadable open weights; the other is API-only.
Side by side
| Claude Haiku 4.5 | GLM-5.3-Flash | |
|---|---|---|
| Provider | Anthropic | Z.ai (Zhipu) |
| Noometry Index | 39.3 | 49.6 |
| Released | 2025-10-15 | 2026-08-20 |
| Weights | Proprietary | Open |
| Context window | 200K | 1M |
| Max output | 64K | 131K |
| Input $ / M tokens | $1 | $0.15 |
| Output $ / M tokens | $5 | $0.50 |
| Results tracked | 53 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.3-Flash leads
Claude Haiku 4.5: 43.9 (#71), GLM-5.3-Flash: 53.7 (#26)
| Benchmark | Claude Haiku 4.5 | GLM-5.3-Flash |
|---|---|---|
| LMArena WebDev | 1330 | 1614 |
| SciCode | 43.3% | 51.6% |
| LMArena Coding | 1454 | 1506 |
| ALE-Bench | 653.48 | 303.55 |
| DeepSWE | — | 63.4% |
| FrontierCode | — | 31.8% |
| SWE-bench Verified (bash only) | 66.6% | — |
| SWE-bench Multilingual | 64.7% | — |
| WeirdML | 45.4% | — |
Agentic & Tool Use Too close to call
Claude Haiku 4.5: 33.5 (#50), GLM-5.3-Flash: 34.3 (#41)
| Benchmark | Claude Haiku 4.5 | GLM-5.3-Flash |
|---|---|---|
| Terminal-Bench | 35.5% | — |
| APEX-Agents | — | 52.8% |
| Berkeley Function Calling Leaderboard | 68.7% | — |
| DeepResearch Bench | 45.5% | — |
| BALROG | 31.2% | — |
| ExploitBench | 13.7% | — |
| GDP.pdf | — | 14% |
| Vending-Bench 2 | 458.89 | — |
Reasoning GLM-5.3-Flash leads
Claude Haiku 4.5: 15.1 (#310), GLM-5.3-Flash: 31.7 (#69)
| Benchmark | Claude Haiku 4.5 | GLM-5.3-Flash |
|---|---|---|
| CritPt | 0% | 15.4% |
| Chess Puzzles | 8% | 14% |
| LMArena Hard Prompts | 1420 | 1490 |
| Epoch Capabilities Index | 142.42 | 151.9 |
| ARC-AGI-2 | 4% | — |
| NYT Connections (extended) | 14.3% | — |
| ARC-AGI-1 | 47.7% | — |
| Mystery Game Puzzles | — | 8% |
| DTBench | 73.6% | — |
| LMCA | 30.9% | — |
| Surface Evolver Bench | — | 52.5% |
| Bench to the Future 3 | — | 0.15 |
| ForecastBench | 61.4 | — |
Math GLM-5.3-Flash leads
Claude Haiku 4.5: 43.0 (#69), GLM-5.3-Flash: 53.1 (#38)
| Benchmark | Claude Haiku 4.5 | GLM-5.3-Flash |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 66.7% | 93.9% |
| LMArena Math | 1395 | 1499 |
| FrontierMath (Tiers 1-3) | — | 55.8% |
| FrontierMath Tier 4 | — | 17.1% |
| ProofBench | — | 21% |
| Omni-MATH | 56.1% | — |
| MATH Level 5 | 96.4% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GLM-5.3-Flash leads
Claude Haiku 4.5: 37.6 (#146), GLM-5.3-Flash: 58.4 (#33)
| Benchmark | Claude Haiku 4.5 | GLM-5.3-Flash |
|---|---|---|
| GPQA Diamond | 71.2% | 90.2% |
| LMArena Expert | 1443 | 1512 |
| SimpleQA Verified | 13.2% | — |
| MMLU-Pro | 77.7% | — |
| Vectara Hallucination Rate | 9.8% | — |
| GPQA (HELM) | 60.5% | — |
Multimodal GLM-5.3-Flash leads
Claude Haiku 4.5: 27.0 (#111), GLM-5.3-Flash: 42.6 (#25)
| Benchmark | Claude Haiku 4.5 | GLM-5.3-Flash |
|---|---|---|
| LMArena Vision | — | 1304 |
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1420 | — |
Multilingual GLM-5.3-Flash leads
Claude Haiku 4.5: 50.1 (#124), GLM-5.3-Flash: 56.2 (#24)
| Benchmark | Claude Haiku 4.5 | GLM-5.3-Flash |
|---|---|---|
| LMArena Non-English | 1376 | 1462 |
| LMArena Chinese | 1415 | 1529 |
| LMArena French | 1408 | 1495 |
| LMArena German | 1377 | 1457 |
| LMArena Japanese | 1339 | 1420 |
| LMArena Korean | 1346 | 1443 |
| LMArena Russian | 1380 | 1472 |
| LMArena Spanish | 1420 | 1471 |
Instruction Following GLM-5.3-Flash leads
Claude Haiku 4.5: 71.6 (#144), GLM-5.3-Flash: 77.8 (#17)
| Benchmark | Claude Haiku 4.5 | GLM-5.3-Flash |
|---|---|---|
| LMArena Instruction Following | 1414 | 1480 |
| IFEval | 80.1% | — |
Long Context GLM-5.3-Flash leads
Claude Haiku 4.5: 43.6 (#86), GLM-5.3-Flash: 45.3 (#41)
| Benchmark | Claude Haiku 4.5 | GLM-5.3-Flash |
|---|---|---|
| LMArena Longer Query | 1427 | 1479 |
Writing & Preference GLM-5.3-Flash leads
Claude Haiku 4.5: 58.1 (#119), GLM-5.3-Flash: 65.4 (#49)
| Benchmark | Claude Haiku 4.5 | GLM-5.3-Flash |
|---|---|---|
| LMArena Text | 1396 | 1471 |
| LMArena Creative Writing | 1371 | 1440 |
| LMArena Multi-Turn | 1409 | 1471 |
| WildBench | 83.9% | — |
| EQ-Bench 4 | 1064 | — |
Frequently asked questions
Is Claude Haiku 4.5 better than GLM-5.3-Flash?
GLM-5.3-Flash is the stronger model overall, scoring 49.6 to 39.3 on the Noometry Index.
Which is cheaper, Claude Haiku 4.5 or GLM-5.3-Flash?
GLM-5.3-Flash is cheaper. It lists at $0.15 per million input tokens and $0.50 per million output tokens; Claude Haiku 4.5 lists at $1 and $5.
Is Claude Haiku 4.5 or GLM-5.3-Flash better for coding?
GLM-5.3-Flash scores higher on coding benchmarks: 53.7 versus 43.9 in the Noometry coding category.
Which has the bigger context window?
GLM-5.3-Flash does, with 1M tokens against 200K.
How many benchmarks do Claude Haiku 4.5 and GLM-5.3-Flash share?
25 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and GLM-5.3-Flash has 36.