GLM-4.6V-Flash vs Claude Haiku 4.5 vs Qwen3 Max
GLM-4.6V-Flash comes out ahead, 63 to 47 and 30 on our weighted score, and it is the cheaper option too.
- Our pick
Z.ai (Zhipu)GLM-4.6V-Flash
63/100- ECI—
- Price$0.161 / $0.559
- Context128K
AnthropicClaude Haiku 4.5
47/100- ECI142.2
- Price$1.00 / $5.00
- Context200K
Alibaba (Qwen)Qwen3 Max
30/100- ECI142.4
- Price$1.20 / $6.00
- Context262K
GLM-4.6V-Flash is our pick
GLM-4.6V-Flash is the better all-round choice, scoring 63/100 against Claude Haiku 4.5 (47) and Qwen3 Max (30). It leads on price. Claude Haiku 4.5 wins on inputs & features. Qwen3 Max wins on context window. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
- CapabilityNot enough dataNo independent benchmark covers every model here yet
- Lowest priceGLM-4.6V-FlashGLM-4.6V-Flash $0.261 · Claude Haiku 4.5 $2.00 · Qwen3 Max $2.40 per 1M tokens (3:1 blend)
- Longest contextQwen3 MaxQwen3 Max 262,144 · Claude Haiku 4.5 200,000 · GLM-4.6V-Flash 128,000 tokens
- Widest inputsGLM-4.6V-Flash and Claude Haiku 4.5GLM-4.6V-Flash: Text, Images, Video · Claude Haiku 4.5: Text, Images, PDFs · Qwen3 Max: Text
- Self-hostingGLM-4.6V-FlashPublishes downloadable weights
| Measure | Weight | GLM-4.6V-Flash | Claude Haiku 4.5 | Qwen3 Max |
|---|---|---|---|---|
| Price | 50% | 74 | 34 | 30 |
| Inputs & features | 30% | 70 | 80 | 25 |
| Context window | 20% | 24 | 32 | 37 |
| Overall | 100% | 63/100 | 47/100 | 30/100 |
Left out because at least one model lacks the data: capability. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | GLM-4.6V-FlashZ.ai (Zhipu) | Claude Haiku 4.5Anthropic | Qwen3 MaxAlibaba (Qwen) |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | 142.2 | 142.4 (best) |
| ECI rank | — | #102 of 165 | #101 of 165 (best) |
| GPQA DiamondGraduate-level science questions | — | 71.2% | 72.6% (best) |
| FrontierMath Tiers 1–3Research-level mathematics | — | — | 19.0% |
| OTIS Mock AIME 2024–2025Competition mathematics | — | 66.7% | 73.3% (best) |
| SimpleQA VerifiedShort factual questions | — | 13.2% | 48.8% (best) |
| Price per million tokens | |||
| Input | $0.161 (best) | $1.00 | $1.20 |
| Output | $0.559 (best) | $5.00 | $6.00 |
| Cached input | — | $0.10 | — |
| Blended (3:1) | $0.261 (best) | $2.00 | $2.40 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 2 providers | Official Anthropic API | Official Alibaba API |
| Limits | |||
| Context window | 128,000 tokens | 200,000 tokens | 262,144 tokens (best) |
| Max output | 32,768 tokens | 64,000 tokens | 65,536 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | No |
| PDFs | No | Yes | No |
| Audio | No | No | No |
| Video | Yes | No | No |
| Reasoning | Yes | Yes | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | Yes | No |
| Availability | |||
| Weights | Open | Proprietary | Proprietary |
| API model ID | glm-4.6v-flash | claude-haiku-4-5 | qwen3-max |
| API providers | 6 | 48 (best) | 13 |
| Released | Dec 8, 2025 | 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-4.6V-Flash$2.73
- Claude Haiku 4.5$20.00
- Qwen3 Max$24.00
Which should you choose?
Which is better: GLM-4.6V-Flash, Claude Haiku 4.5 or Qwen3 Max?
GLM-4.6V-Flash is the better all-round choice, scoring 63/100 against Claude Haiku 4.5 (47) and Qwen3 Max (30). It leads on price. Claude Haiku 4.5 wins on inputs & features. Qwen3 Max wins on context window. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, GLM-4.6V-Flash, Claude Haiku 4.5 or Qwen3 Max?
GLM-4.6V-Flash is cheaper at $0.161 input / $0.559 output per million tokens (median across 2 API providers; free on Z.AI). Claude Haiku 4.5 costs $1.00 input / $5.00 output per million tokens (official Anthropic 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 $0.261 per million tokens for GLM-4.6V-Flash versus $2.00 for Claude Haiku 4.5 (7.7× as much) and $2.40 for Qwen3 Max (9.2× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. GLM-4.6V-Flash has not been scored yet, Claude Haiku 4.5 has an ECI of 142.2 and Qwen3 Max has an ECI of 142.4.
Which is better for coding?
There are no published SWE-bench Verified results for GLM-4.6V-Flash, Claude Haiku 4.5 and Qwen3 Max yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. 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 Claude Haiku 4.5 and 128,000 for GLM-4.6V-Flash. Maximum output per response: GLM-4.6V-Flash up to 32,768, Claude Haiku 4.5 up to 64,000, Qwen3 Max up to 65,536 tokens.
Which can read images, PDFs, audio or video?
GLM-4.6V-Flash accepts text, images and video; Claude Haiku 4.5 accepts text, images and PDFs; Qwen3 Max accepts text. GLM-4.6V-Flash handles the widest range of inputs.
Are any of these open source?
GLM-4.6V-Flash publishes its weights and can be self-hosted; Claude Haiku 4.5 and Qwen3 Max is proprietary.
Which is newer?
GLM-4.6V-Flash is the newest, released Dec 8, 2025. 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 Nov 2, 2026.
