Model comparison
Claude Haiku 4.5 vs GLM-5V-Turbo
GLM-5V-Turbo is the stronger model overall, scoring 43.8 to 39.5 on the Noometry Index.
Last verified . 18 shared benchmarks.
Summary
- They share 18 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 2 categories and GLM-5V-Turbo in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-5V-Turbo leads 29.7 to 15.1.
- GLM-5V-Turbo is cheaper at $1.20 / $4 per million input/output tokens, against $1 / $5 for Claude Haiku 4.5.
Side by side
| Claude Haiku 4.5 | GLM-5V-Turbo | |
|---|---|---|
| Provider | Anthropic | Z.ai (Zhipu) |
| Noometry Index | 39.5 | 43.8 |
| Released | 2025-10-15 | 2026-04-01 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 200K |
| Max output | 64K | 131K |
| Input $ / M tokens | $1 | $1.20 |
| Output $ / M tokens | $5 | $4 |
| Results tracked | 53 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Haiku 4.5 leads
Claude Haiku 4.5: 44.0 (#78), GLM-5V-Turbo: 42.1 (#111)
| Benchmark | Claude Haiku 4.5 | GLM-5V-Turbo |
|---|---|---|
| LMArena WebDev | 1330 | 1401 |
| LMArena Coding | 1453 | 1466 |
| SWE-bench Verified (bash only) | 66.6% | — |
| SWE-bench Multilingual | 64.7% | — |
| SciCode | 43.3% | — |
| WeirdML | 45.4% | — |
| ALE-Bench | 653.48 | — |
Agentic & Tool Use Not comparable
Claude Haiku 4.5: 33.6 (#52), GLM-5V-Turbo: —
| Benchmark | Claude Haiku 4.5 | GLM-5V-Turbo |
|---|---|---|
| Terminal-Bench | 35.5% | — |
| Berkeley Function Calling Leaderboard | 68.7% | — |
| DeepResearch Bench | 45.5% | — |
| BALROG | 31.2% | — |
| ExploitBench | 13.7% | — |
| Vending-Bench 2 | 458.89 | — |
Reasoning GLM-5V-Turbo leads
Claude Haiku 4.5: 15.1 (#320), GLM-5V-Turbo: 29.7 (#89)
| Benchmark | Claude Haiku 4.5 | GLM-5V-Turbo |
|---|---|---|
| LMArena Hard Prompts | 1420 | 1443 |
| ARC-AGI-2 | 4% | — |
| NYT Connections (extended) | 14.3% | — |
| ARC-AGI-1 | 47.7% | — |
| CritPt | 0% | — |
| Chess Puzzles | 8% | — |
| DTBench | 73.6% | — |
| LMCA | 30.9% | — |
| Epoch Capabilities Index | 142.41 | — |
| ForecastBench | 61.4 | — |
Math Claude Haiku 4.5 leads
Claude Haiku 4.5: 44.9 (#78), GLM-5V-Turbo: 39.4 (#106)
| Benchmark | Claude Haiku 4.5 | GLM-5V-Turbo |
|---|---|---|
| LMArena Math | 1396 | 1441 |
| OTIS Mock AIME 2024-2025 | 66.7% | — |
| Omni-MATH | 56.1% | — |
| MATH Level 5 | 96.4% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GLM-5V-Turbo leads
Claude Haiku 4.5: 37.7 (#153), GLM-5V-Turbo: 40.6 (#117)
| Benchmark | Claude Haiku 4.5 | GLM-5V-Turbo |
|---|---|---|
| LMArena Expert | 1442 | 1452 |
| GPQA Diamond | 71.2% | — |
| SimpleQA Verified | 13.2% | — |
| MMLU-Pro | 77.7% | — |
| Vectara Hallucination Rate | 9.8% | — |
| GPQA (HELM) | 60.5% | — |
Multimodal GLM-5V-Turbo leads
Claude Haiku 4.5: 26.8 (#118), GLM-5V-Turbo: 40.9 (#42)
| Benchmark | Claude Haiku 4.5 | GLM-5V-Turbo |
|---|---|---|
| LMArena Document | 1420 | 1416 |
| LMArena Vision | — | 1264 |
| Blueprint-Bench 2 | 0% | — |
Multilingual GLM-5V-Turbo leads
Claude Haiku 4.5: 49.9 (#129), GLM-5V-Turbo: 53.0 (#73)
| Benchmark | Claude Haiku 4.5 | GLM-5V-Turbo |
|---|---|---|
| LMArena Non-English | 1377 | 1420 |
| LMArena Chinese | 1417 | 1488 |
| LMArena French | 1408 | 1444 |
| LMArena German | 1375 | 1423 |
| LMArena Korean | 1347 | 1396 |
| LMArena Russian | 1381 | 1431 |
| LMArena Spanish | 1420 | 1450 |
| LMArena Japanese | 1339 | — |
Instruction Following GLM-5V-Turbo leads
Claude Haiku 4.5: 71.4 (#149), GLM-5V-Turbo: 75.0 (#80)
| Benchmark | Claude Haiku 4.5 | GLM-5V-Turbo |
|---|---|---|
| LMArena Instruction Following | 1414 | 1423 |
| IFEval | 80.1% | — |
Long Context Too close to call
Claude Haiku 4.5: 43.6 (#92), GLM-5V-Turbo: 44.0 (#80)
| Benchmark | Claude Haiku 4.5 | GLM-5V-Turbo |
|---|---|---|
| LMArena Longer Query | 1427 | 1438 |
Writing & Preference GLM-5V-Turbo leads
Claude Haiku 4.5: 57.9 (#123), GLM-5V-Turbo: 62.5 (#73)
| Benchmark | Claude Haiku 4.5 | GLM-5V-Turbo |
|---|---|---|
| LMArena Text | 1396 | 1437 |
| LMArena Creative Writing | 1372 | 1416 |
| LMArena Multi-Turn | 1409 | 1432 |
| WildBench | 83.9% | — |
| EQ-Bench 4 | 1064 | — |
Frequently asked questions
Is Claude Haiku 4.5 better than GLM-5V-Turbo?
GLM-5V-Turbo is the stronger model overall, scoring 43.8 to 39.5 on the Noometry Index.
Which is cheaper, Claude Haiku 4.5 or GLM-5V-Turbo?
GLM-5V-Turbo is cheaper. It lists at $1.20 per million input tokens and $4 per million output tokens; Claude Haiku 4.5 lists at $1 and $5.
Is Claude Haiku 4.5 or GLM-5V-Turbo better for coding?
Claude Haiku 4.5 scores higher on coding benchmarks: 44.0 versus 42.1 in the Noometry coding category.
Which has the bigger context window?
Both accept 200K tokens.
How many benchmarks do Claude Haiku 4.5 and GLM-5V-Turbo share?
18 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and GLM-5V-Turbo has 19.