Qwen3 VL 235B A22B Instruct vs Claude Haiku 4.5 vs MiniMax-M2
Qwen3 VL 235B A22B Instruct comes out ahead, 53 to 48 and 48 on our weighted score, though MiniMax-M2 is 14% cheaper per token.
- Our pick
Alibaba (Qwen)Qwen3 VL 235B A22B Instruct
53/100- ECI—
- Price$0.30 / $1.55
- Context131K
AnthropicClaude Haiku 4.5
48/100- ECI142.4
- Price$1.00 / $5.00
- Context200K
MiniMaxMiniMax-M2
48/100- ECI—
- Price$0.30 / $1.20
- Context205K
Qwen3 VL 235B A22B Instruct is our pick
Qwen3 VL 235B A22B Instruct is the better all-round choice, scoring 53/100 against MiniMax-M2 (48) and Claude Haiku 4.5 (48). Claude Haiku 4.5 wins on inputs & features. MiniMax-M2 wins on price. 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 priceMiniMax-M2MiniMax-M2 $0.525 · Qwen3 VL 235B A22B Instruct $0.613 · Claude Haiku 4.5 $2.00 per 1M tokens (3:1 blend)
- Longest contextMiniMax-M2MiniMax-M2 204,800 · Claude Haiku 4.5 200,000 · Qwen3 VL 235B A22B Instruct 131,072 tokens
- Widest inputsClaude Haiku 4.5Qwen3 VL 235B A22B Instruct: Text, Images · Claude Haiku 4.5: Text, Images, PDFs · MiniMax-M2: Text
- Self-hostingQwen3 VL 235B A22B Instruct and MiniMax-M2Publishes downloadable weights
| Measure | Weight | Qwen3 VL 235B A22B Instruct | Claude Haiku 4.5 | MiniMax-M2 |
|---|---|---|---|---|
| Price | 50% | 60 | 36 | 63 |
| Inputs & features | 30% | 60 | 80 | 35 |
| Context window | 20% | 24 | 32 | 32 |
| Overall | 100% | 53/100 | 48/100 | 48/100 |
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 | Qwen3 VL 235B A22B InstructAlibaba (Qwen) | Claude Haiku 4.5Anthropic | MiniMax-M2MiniMax |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | 142.4 | — |
| ECI rank | — | #90 of 148 | — |
| GPQA DiamondGraduate-level science questions | — | 71.2% | — |
| OTIS Mock AIME 2024–2025Competition mathematics | — | 66.7% | — |
| SimpleQA VerifiedShort factual questions | — | 13.2% | — |
| Price per million tokens | |||
| Input | $0.30 (best) | $1.00 | $0.30 (best) |
| Output | $1.55 | $5.00 | $1.20 (best) |
| Cached input | — | $0.10 | — |
| Blended (3:1) | $0.613 | $2.00 | $0.525 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 12 providers | Official Anthropic API | Official MiniMax (minimax.io) API |
| Limits | |||
| Context window | 131,072 tokens | 200,000 tokens | 204,800 tokens (best) |
| Max output | 32,768 tokens | 64,000 tokens | 131,072 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | No |
| PDFs | No | Yes | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | Yes | No |
| Availability | |||
| Weights | Open | Proprietary | Open |
| API model ID | — | claude-haiku-4-5 | MiniMax-M2 |
| API providers | 12 | 34 (best) | 13 |
| Released | Sep 23, 2025 | Oct 15, 2025 | Oct 27, 2025 |
| Knowledge cutoff | Mar 31, 2025 | Feb 28, 2025 | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Qwen3 VL 235B A22B Instruct$6.10
- Claude Haiku 4.5$20.00
- MiniMax-M2$5.40
Which should you choose?
Which is better: Qwen3 VL 235B A22B Instruct, Claude Haiku 4.5 or MiniMax-M2?
Qwen3 VL 235B A22B Instruct is the better all-round choice, scoring 53/100 against MiniMax-M2 (48) and Claude Haiku 4.5 (48). Claude Haiku 4.5 wins on inputs & features. MiniMax-M2 wins on price. 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, Qwen3 VL 235B A22B Instruct, Claude Haiku 4.5 or MiniMax-M2?
MiniMax-M2 is cheaper at $0.30 input / $1.20 output per million tokens (official MiniMax (minimax.io) API price). Qwen3 VL 235B A22B Instruct costs $0.30 input / $1.55 output per million tokens (median across 12 API providers); Claude Haiku 4.5 costs $1.00 input / $5.00 output per million tokens (official Anthropic API price). At a typical mix of three input tokens to one output token, that is $0.525 per million tokens for MiniMax-M2 versus $0.613 for Qwen3 VL 235B A22B Instruct (1.2× as much) and $2.00 for Claude Haiku 4.5 (3.8× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Qwen3 VL 235B A22B Instruct has not been scored yet, Claude Haiku 4.5 has an ECI of 142.4 and MiniMax-M2 has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Qwen3 VL 235B A22B Instruct, Claude Haiku 4.5 and MiniMax-M2 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?
MiniMax-M2 has the largest context window at 204,800 tokens, against 200,000 for Claude Haiku 4.5 and 131,072 for Qwen3 VL 235B A22B Instruct. Maximum output per response: Qwen3 VL 235B A22B Instruct up to 32,768, Claude Haiku 4.5 up to 64,000, MiniMax-M2 up to 131,072 tokens.
Which can read images, PDFs, audio or video?
Qwen3 VL 235B A22B Instruct accepts text and images; Claude Haiku 4.5 accepts text, images and PDFs; MiniMax-M2 accepts text. Claude Haiku 4.5 handles the widest range of inputs.
Are any of these open source?
Qwen3 VL 235B A22B Instruct and MiniMax-M2 publishes its weights and can be self-hosted; Claude Haiku 4.5 is proprietary.
Which is newer?
MiniMax-M2 is the newest, released Oct 27, 2025. Claude Haiku 4.5 came out Oct 15, 2025; Qwen3 VL 235B A22B Instruct came out Sep 23, 2025. Knowledge cutoff: Qwen3 VL 235B A22B Instruct Mar 31, 2025, Claude Haiku 4.5 Feb 28, 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.
Related comparisons
- Qwen3 VL 235B A22B Instruct vs GPT-5.1 Codex miniOpenAI
- Qwen3 VL 235B A22B Instruct vs Mistral Medium 3.1Mistral AI
- Qwen3 VL 235B A22B Instruct vs Gemma-SEA-LION-v4-27B-ITAI Singapore
- Claude Haiku 4.5 vs Qwen3 MaxAlibaba (Qwen) · ECI 142.4
- Claude Haiku 4.5 vs GLM-4.7Z.ai (Zhipu) · ECI 143.5
- Claude Haiku 4.5 vs Mistral Medium 3.5Mistral AI · ECI 141.4
