GLM-5.1 vs Claude Haiku 4.5 vs Qwen3 Max
Too close to call on our weighted score (Claude Haiku 4.5 58, GLM-5.1 57, Qwen3 Max 50). The right pick depends on what you value most.
Z.ai (Zhipu)GLM-5.1
57/100- ECI149.9
- Price$1.40 / $4.40
- Context200K
AnthropicClaude Haiku 4.5
58/100- ECI142.4
- Price$1.00 / $5.00
- Context200K
Alibaba (Qwen)Qwen3 Max
50/100- ECI142.4
- Price$1.20 / $6.00
- Context262K
Too close to call
It is close. Our weighted score puts them within a point (Claude Haiku 4.5 58/100, GLM-5.1 57/100, Qwen3 Max 50/100), so choose by what matters most for your work: GLM-5.1 for raw capability, Claude Haiku 4.5 on price and Qwen3 Max for long inputs. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- CapabilityGLM-5.1Capabilities Index (ECI): GLM-5.1 149.9 · Claude Haiku 4.5 142.4 · Qwen3 Max 142.4
- Lowest priceClaude Haiku 4.5Claude Haiku 4.5 $2.00 · GLM-5.1 $2.15 · Qwen3 Max $2.40 per 1M tokens (3:1 blend)
- Longest contextQwen3 MaxQwen3 Max 262,144 · GLM-5.1 200,000 · Claude Haiku 4.5 200,000 tokens
- Widest inputsClaude Haiku 4.5GLM-5.1: Text · Claude Haiku 4.5: Text, Images, PDFs · Qwen3 Max: Text
- Self-hostingGLM-5.1Publishes downloadable weights
| Measure | Weight | GLM-5.1 | Claude Haiku 4.5 | Qwen3 Max |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 78 | 69 | 68 |
| Price | 25% | 34 | 36 | 32 |
| Inputs & features | 15% | 45 | 80 | 25 |
| Context window | 10% | 32 | 32 | 37 |
| Overall | 100% | 57/100 | 58/100 | 50/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | GLM-5.1Z.ai (Zhipu) | Claude Haiku 4.5Anthropic | Qwen3 MaxAlibaba (Qwen) |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 149.9 (best) | 142.4 | 142.4 |
| ECI rank | #51 of 148 (best) | #90 of 148 | #91 of 148 |
| GPQA DiamondGraduate-level science questions | 89.9% (best) | 71.2% | 72.6% |
| FrontierMath Tiers 1–3Research-level mathematics | 36.8% (best) | — | 19.0% |
| OTIS Mock AIME 2024–2025Competition mathematics | 93.3% (best) | 66.7% | 73.3% |
| SWE-bench VerifiedFixing real GitHub issues | 74.2% | — | — |
| SimpleQA VerifiedShort factual questions | 34.0% | 13.2% | 48.8% (best) |
| Price per million tokens | |||
| Input | $1.40 | $1.00 (best) | $1.20 |
| Output | $4.40 (best) | $5.00 | $6.00 |
| Cached input | $0.26 | $0.10 (best) | — |
| Blended (3:1) | $2.15 | $2.00 (best) | $2.40 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Z.AI API | Official Anthropic API | Official Alibaba API |
| Limits | |||
| Context window | 200,000 tokens | 200,000 tokens | 262,144 tokens (best) |
| Max output | 131,072 tokens (best) | 64,000 tokens | 65,536 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | No |
| PDFs | No | Yes | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yes | Yes | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | Yes | No |
| Availability | |||
| Weights | Open | Proprietary | Proprietary |
| API model ID | glm-5.1 | claude-haiku-4-5 | qwen3-max |
| API providers | 40 (best) | 34 | 16 |
| Released | Apr 7, 2026 | Oct 15, 2025 | Sep 23, 2025 |
| Knowledge cutoff | — | Feb 28, 2025 | Apr 2025 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- GLM-5.1$22.80
- Claude Haiku 4.5$20.00
- Qwen3 Max$24.00
Which should you choose?
Which is better: GLM-5.1, Claude Haiku 4.5 or Qwen3 Max?
It is close. Our weighted score puts them within a point (Claude Haiku 4.5 58/100, GLM-5.1 57/100, Qwen3 Max 50/100), so choose by what matters most for your work: GLM-5.1 for raw capability, Claude Haiku 4.5 on price and Qwen3 Max for long inputs. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, GLM-5.1, Claude Haiku 4.5 or Qwen3 Max?
Claude Haiku 4.5 is cheaper at $1.00 input / $5.00 output per million tokens (official Anthropic API price). GLM-5.1 costs $1.40 input / $4.40 output per million tokens (official Z.AI API price); Qwen3 Max costs $1.20 input / $6.00 output per million tokens (official Alibaba API price). At a typical mix of three input tokens to one output token, that is $2.00 per million tokens for Claude Haiku 4.5 versus $2.15 for GLM-5.1 (1.1× as much) and $2.40 for Qwen3 Max (1.2× as much).
Which scores higher on benchmarks?
GLM-5.1 scores higher on the Capabilities Index (ECI): GLM-5.1 149.9 (#51 of 148), Claude Haiku 4.5 142.4 (#90 of 148) and Qwen3 Max 142.4 (#91 of 148). Their confidence ranges do not overlap (148.0–151.6 vs 139.5–144.3), so the gap is a real one. On individual benchmarks: GPQA Diamond — GLM-5.1 89.9%, Qwen3 Max 72.6%, Claude Haiku 4.5 71.2%; OTIS Mock AIME 2024–2025 — GLM-5.1 93.3%, Qwen3 Max 73.3%, Claude Haiku 4.5 66.7%; SimpleQA Verified — Qwen3 Max 48.8%, GLM-5.1 34.0%, Claude Haiku 4.5 13.2%.
Which is better for coding?
There are no published SWE-bench Verified results for Claude Haiku 4.5 and Qwen3 Max yet, so there is no like-for-like coding score. On overall capability, GLM-5.1 leads, which tends to carry over to coding, but test on your own codebase. All three support tool calling for agent workflows.
Which has the bigger context window?
Qwen3 Max has the largest context window at 262,144 tokens, against 200,000 for GLM-5.1 and 200,000 for Claude Haiku 4.5. Maximum output per response: GLM-5.1 up to 131,072, Claude Haiku 4.5 up to 64,000, Qwen3 Max up to 65,536 tokens.
Which can read images, PDFs, audio or video?
GLM-5.1 accepts text; Claude Haiku 4.5 accepts text, images and PDFs; Qwen3 Max accepts text. Claude Haiku 4.5 handles the widest range of inputs.
Are any of these open source?
GLM-5.1 publishes its weights and can be self-hosted; Claude Haiku 4.5 and Qwen3 Max is proprietary.
Which is newer?
GLM-5.1 is the newest, released Apr 7, 2026. Claude Haiku 4.5 came out Oct 15, 2025; Qwen3 Max came out Sep 23, 2025. Knowledge cutoff: Claude Haiku 4.5 Feb 28, 2025, Qwen3 Max Apr 2025.
How do you decide the winner?
Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Oct 4, 2026.
