Model comparison
Claude Haiku 4.5 vs GLM-5.1
GLM-5.1 is the stronger model overall, scoring 47.8 to 39.5 on the Noometry Index.
Last verified . 32 shared benchmarks.
Summary
- They share 32 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 1 category and GLM-5.1 in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-5.1 leads 39.1 to 15.1.
- The biggest single-benchmark swing is NYT Connections (extended): 14.3% for Claude Haiku 4.5 and 77.7% for GLM-5.1.
- Claude Haiku 4.5 is cheaper at $1 / $5 per million input/output tokens, against $1.40 / $4.40 for GLM-5.1.
- GLM-5.1 has downloadable open weights; the other is API-only.
Side by side
| Claude Haiku 4.5 | GLM-5.1 | |
|---|---|---|
| Provider | Anthropic | Z.ai (Zhipu) |
| Noometry Index | 39.5 | 47.8 |
| Released | 2025-10-15 | 2026-04-07 |
| Weights | Proprietary | Open |
| Context window | 200K | 200K |
| Max output | 64K | 131K |
| Input $ / M tokens | $1 | $1.40 |
| Output $ / M tokens | $5 | $4.40 |
| Results tracked | 53 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.1 leads
Claude Haiku 4.5: 44.0 (#78), GLM-5.1: 48.7 (#55)
| Benchmark | Claude Haiku 4.5 | GLM-5.1 |
|---|---|---|
| LMArena WebDev | 1330 | 1508 |
| SciCode | 43.3% | 43.8% |
| WeirdML | 45.4% | 57.1% |
| LMArena Coding | 1453 | 1485 |
| ALE-Bench | 653.48 | 887.1 |
| SWE-bench Verified | — | 74.2% |
| SWE-bench Verified (bash only) | 66.6% | — |
| SWE-bench Multilingual | 64.7% | — |
Agentic & Tool Use Claude Haiku 4.5 leads
Claude Haiku 4.5: 33.6 (#52), GLM-5.1: 24.9 (#113)
| Benchmark | Claude Haiku 4.5 | GLM-5.1 |
|---|---|---|
| ExploitBench | 13.7% | 18.1% |
| Vending-Bench 2 | 458.89 | 5,634 |
| Terminal-Bench | 35.5% | — |
| APEX-Agents | — | 40.9% |
| Berkeley Function Calling Leaderboard | 68.7% | — |
| DeepResearch Bench | 45.5% | — |
| BALROG | 31.2% | — |
| GBAEval | — | 0% |
Reasoning GLM-5.1 leads
Claude Haiku 4.5: 15.1 (#320), GLM-5.1: 39.1 (#60)
| Benchmark | Claude Haiku 4.5 | GLM-5.1 |
|---|---|---|
| NYT Connections (extended) | 14.3% | 77.7% |
| CritPt | 0% | 4.6% |
| Chess Puzzles | 8% | 19% |
| LMArena Hard Prompts | 1420 | 1472 |
| Epoch Capabilities Index | 142.41 | 149.84 |
| ARC-AGI-2 | 4% | — |
| SimpleBench | — | 55.1% |
| ARC-AGI-1 | 47.7% | — |
| Thematic Generalization | — | 69.8% |
| DTBench | 73.6% | — |
| LMCA | 30.9% | — |
| ForecastBench | 61.4 | — |
Math GLM-5.1 leads
Claude Haiku 4.5: 44.9 (#78), GLM-5.1: 49.7 (#60)
| Benchmark | Claude Haiku 4.5 | GLM-5.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 66.7% | 93.3% |
| LMArena Math | 1396 | 1473 |
| FrontierMath (Feb 2025 set) | 5.9% | 33.4% |
| FrontierMath Tier 4 (v1) | 2.1% | 12.5% |
| FrontierMath (Tiers 1-3) | — | 36.8% |
| MathArena Final-Answer Competitions | — | 67.1% |
| ProofBench | — | 22.2% |
| Omni-MATH | 56.1% | — |
| MATH Level 5 | 96.4% | — |
Knowledge GLM-5.1 leads
Claude Haiku 4.5: 37.7 (#153), GLM-5.1: 54.9 (#50)
| Benchmark | Claude Haiku 4.5 | GLM-5.1 |
|---|---|---|
| GPQA Diamond | 71.2% | 89.9% |
| SimpleQA Verified | 13.2% | 34% |
| LMArena Expert | 1442 | 1476 |
| MMLU-Pro | 77.7% | — |
| Vectara Hallucination Rate | 9.8% | — |
| GPQA (HELM) | 60.5% | — |
Multimodal Not comparable
Claude Haiku 4.5: 26.8 (#118), GLM-5.1: —
| Benchmark | Claude Haiku 4.5 | GLM-5.1 |
|---|---|---|
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1420 | — |
Multilingual GLM-5.1 leads
Claude Haiku 4.5: 49.9 (#129), GLM-5.1: 55.0 (#36)
| Benchmark | Claude Haiku 4.5 | GLM-5.1 |
|---|---|---|
| LMArena Non-English | 1377 | 1447 |
| LMArena Chinese | 1417 | 1515 |
| LMArena French | 1408 | 1474 |
| LMArena German | 1375 | 1465 |
| LMArena Japanese | 1339 | 1434 |
| LMArena Korean | 1347 | 1418 |
| LMArena Russian | 1381 | 1454 |
| LMArena Spanish | 1420 | 1469 |
Instruction Following GLM-5.1 leads
Claude Haiku 4.5: 71.4 (#149), GLM-5.1: 76.3 (#42)
| Benchmark | Claude Haiku 4.5 | GLM-5.1 |
|---|---|---|
| LMArena Instruction Following | 1414 | 1451 |
| IFEval | 80.1% | — |
Long Context GLM-5.1 leads
Claude Haiku 4.5: 43.6 (#92), GLM-5.1: 44.9 (#53)
| Benchmark | Claude Haiku 4.5 | GLM-5.1 |
|---|---|---|
| LMArena Longer Query | 1427 | 1466 |
Writing & Preference GLM-5.1 leads
Claude Haiku 4.5: 57.9 (#123), GLM-5.1: 66.9 (#31)
| Benchmark | Claude Haiku 4.5 | GLM-5.1 |
|---|---|---|
| LMArena Text | 1396 | 1461 |
| LMArena Creative Writing | 1372 | 1453 |
| LMArena Multi-Turn | 1409 | 1472 |
| EQ-Bench Creative Writing | — | 1592 |
| WildBench | 83.9% | — |
| EQ-Bench 4 | 1064 | — |
Frequently asked questions
Is Claude Haiku 4.5 better than GLM-5.1?
GLM-5.1 is the stronger model overall, scoring 47.8 to 39.5 on the Noometry Index.
Which is cheaper, Claude Haiku 4.5 or GLM-5.1?
Claude Haiku 4.5 is cheaper. It lists at $1 per million input tokens and $5 per million output tokens; GLM-5.1 lists at $1.40 and $4.40.
Is Claude Haiku 4.5 or GLM-5.1 better for coding?
GLM-5.1 scores higher on coding benchmarks: 48.7 versus 44.0 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-5.1 share?
32 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and GLM-5.1 has 41.