Model comparison
Claude Haiku 4.5 vs GLM-4.6V
GLM-4.6V is the stronger model overall, scoring 41.3 to 39.5 on the Noometry Index.
Last verified . 11 shared benchmarks.
Summary
- They share 11 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 5 categories and GLM-4.6V in 3 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-4.6V leads 27.6 to 15.1.
- GLM-4.6V is cheaper at $0.30 / $0.90 per million input/output tokens, against $1 / $5 for Claude Haiku 4.5.
- Claude Haiku 4.5 accepts more context: 200K tokens versus 128K.
- GLM-4.6V has downloadable open weights; the other is API-only.
Side by side
| Claude Haiku 4.5 | GLM-4.6V | |
|---|---|---|
| Provider | Anthropic | Z.ai (Zhipu) |
| Noometry Index | 39.5 | 41.3 |
| Released | 2025-10-15 | 2025-12-08 |
| Weights | Proprietary | Open |
| Context window | 200K | 128K |
| Max output | 64K | 33K |
| Input $ / M tokens | $1 | $0.30 |
| Output $ / M tokens | $5 | $0.90 |
| Results tracked | 53 | 12 |
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-4.6V: 40.9 (#128)
| Benchmark | Claude Haiku 4.5 | GLM-4.6V |
|---|---|---|
| LMArena Coding | 1453 | 1390 |
| SWE-bench Verified (bash only) | 66.6% | — |
| LMArena WebDev | 1330 | — |
| 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-4.6V: —
| Benchmark | Claude Haiku 4.5 | GLM-4.6V |
|---|---|---|
| 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-4.6V leads
Claude Haiku 4.5: 15.1 (#320), GLM-4.6V: 27.6 (#115)
| Benchmark | Claude Haiku 4.5 | GLM-4.6V |
|---|---|---|
| LMArena Hard Prompts | 1420 | 1368 |
| 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 Not comparable
Claude Haiku 4.5: 44.9 (#78), GLM-4.6V: —
| Benchmark | Claude Haiku 4.5 | GLM-4.6V |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 66.7% | — |
| Omni-MATH | 56.1% | — |
| LMArena Math | 1396 | — |
| MATH Level 5 | 96.4% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Too close to call
Claude Haiku 4.5: 37.7 (#153), GLM-4.6V: 38.0 (#149)
| Benchmark | Claude Haiku 4.5 | GLM-4.6V |
|---|---|---|
| LMArena Expert | 1442 | 1371 |
| GPQA Diamond | 71.2% | — |
| SimpleQA Verified | 13.2% | — |
| MMLU-Pro | 77.7% | — |
| Vectara Hallucination Rate | 9.8% | — |
| GPQA (HELM) | 60.5% | — |
Multimodal GLM-4.6V leads
Claude Haiku 4.5: 26.8 (#118), GLM-4.6V: 34.8 (#90)
| Benchmark | Claude Haiku 4.5 | GLM-4.6V |
|---|---|---|
| LMArena Vision | — | 1164 |
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1420 | — |
Multilingual Claude Haiku 4.5 leads
Claude Haiku 4.5: 49.9 (#129), GLM-4.6V: 48.6 (#141)
| Benchmark | Claude Haiku 4.5 | GLM-4.6V |
|---|---|---|
| LMArena Non-English | 1377 | 1359 |
| LMArena Chinese | 1417 | 1425 |
| LMArena Russian | 1381 | 1340 |
| LMArena French | 1408 | — |
| LMArena German | 1375 | — |
| LMArena Japanese | 1339 | — |
| LMArena Korean | 1347 | — |
| LMArena Spanish | 1420 | — |
Instruction Following Too close to call
Claude Haiku 4.5: 71.4 (#149), GLM-4.6V: 71.4 (#151)
| Benchmark | Claude Haiku 4.5 | GLM-4.6V |
|---|---|---|
| LMArena Instruction Following | 1414 | 1352 |
| IFEval | 80.1% | — |
Long Context Claude Haiku 4.5 leads
Claude Haiku 4.5: 43.6 (#92), GLM-4.6V: 41.3 (#143)
| Benchmark | Claude Haiku 4.5 | GLM-4.6V |
|---|---|---|
| LMArena Longer Query | 1427 | 1358 |
Writing & Preference Claude Haiku 4.5 leads
Claude Haiku 4.5: 57.9 (#123), GLM-4.6V: 56.6 (#137)
| Benchmark | Claude Haiku 4.5 | GLM-4.6V |
|---|---|---|
| LMArena Text | 1396 | 1377 |
| LMArena Creative Writing | 1372 | 1347 |
| LMArena Multi-Turn | 1409 | 1360 |
| WildBench | 83.9% | — |
| EQ-Bench 4 | 1064 | — |
Frequently asked questions
Is Claude Haiku 4.5 better than GLM-4.6V?
GLM-4.6V is the stronger model overall, scoring 41.3 to 39.5 on the Noometry Index.
Which is cheaper, Claude Haiku 4.5 or GLM-4.6V?
GLM-4.6V is cheaper. It lists at $0.30 per million input tokens and $0.90 per million output tokens; Claude Haiku 4.5 lists at $1 and $5.
Is Claude Haiku 4.5 or GLM-4.6V better for coding?
Claude Haiku 4.5 scores higher on coding benchmarks: 44.0 versus 40.9 in the Noometry coding category.
Which has the bigger context window?
Claude Haiku 4.5 does, with 200K tokens against 128K.
How many benchmarks do Claude Haiku 4.5 and GLM-4.6V share?
11 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and GLM-4.6V has 12.