GPT-5.3 Codex vs Qwen3.8 Max vs Claude Sonnet 5
Qwen3.8 Max comes out ahead, 69 to 66 and 64 on our weighted score, and it is the cheaper option too.
OpenAIGPT-5.3 Codex
64/100- ECI156.8
- Price$1.75 / $14.00
- Context400K
- Our pick
Alibaba (Qwen)Qwen3.8 Max
69/100- ECI156.6
- Price$2.00 / $6.00
- Context1M
AnthropicClaude Sonnet 5
66/100- ECI156.3
- Price$2.00 / $10.00
- Context1M
Qwen3.8 Max is our pick
Qwen3.8 Max is the better all-round choice, scoring 69/100 against Claude Sonnet 5 (66) and GPT-5.3 Codex (64). It leads on price and inputs & features. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- CapabilityGPT-5.3 CodexCapabilities Index (ECI): GPT-5.3 Codex 156.8 · Qwen3.8 Max 156.6 · Claude Sonnet 5 156.3
- Lowest priceQwen3.8 MaxQwen3.8 Max $3.00 · Claude Sonnet 5 $4.00 · GPT-5.3 Codex $4.81 per 1M tokens (3:1 blend)
- Longest contextQwen3.8 Max and Claude Sonnet 5Qwen3.8 Max 1,000,000 · Claude Sonnet 5 1,000,000 · GPT-5.3 Codex 400,000 tokens
- Widest inputsQwen3.8 MaxGPT-5.3 Codex: Text, Images, PDFs · Qwen3.8 Max: Text, Images, PDFs, Video · Claude Sonnet 5: Text, Images, PDFs
- Self-hostingNo open weightsAll three are available only through APIs
| Measure | Weight | GPT-5.3 Codex | Qwen3.8 Max | Claude Sonnet 5 |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 87 | 86 | 86 |
| Price | 25% | 18 | 27 | 21 |
| Inputs & features | 15% | 80 | 90 | 80 |
| Context window | 10% | 44 | 60 | 60 |
| Overall | 100% | 64/100 | 69/100 | 66/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | GPT-5.3 CodexOpenAI | Qwen3.8 MaxAlibaba (Qwen) | Claude Sonnet 5Anthropic |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 156.8 (best) | 156.6 | 156.3 |
| ECI rank | #18 of 148 (best) | #20 of 148 | #23 of 148 |
| GPQA DiamondGraduate-level science questions | — | 92.7% (best) | 90.5% |
| FrontierMath Tiers 1–3Research-level mathematics | — | 74.7% (best) | 65.6% |
| OTIS Mock AIME 2024–2025Competition mathematics | — | 99.4% (best) | 94.7% |
| SWE-bench VerifiedFixing real GitHub issues | 74.8% | — | — |
| SimpleQA VerifiedShort factual questions | — | 45.8% (best) | 33.7% |
| Price per million tokens | |||
| Input | $1.75 (best) | $2.00 | $2.00 |
| Output | $14.00 | $6.00 (best) | $10.00 |
| Cached input | $0.175 (best) | $0.25 | $0.20 |
| Blended (3:1) | $4.81 | $3.00 (best) | $4.00 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official OpenAI API | Official Alibaba API | Official Anthropic API |
| Limits | |||
| Context window | 400,000 tokens | 1,000,000 tokens (best) | 1,000,000 tokens (best) |
| Max output | 128,000 tokens | 131,072 tokens (best) | 128,000 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | Yes |
| PDFs | Yes | Yes | Yes |
| Audio | No | No | No |
| Video | No | Yes | No |
| Reasoning | Yeslow · medium · high · xhigh | Yeslow · medium · xhigh | Yeslow · medium · high · xhigh · max |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | Yes | Yes |
| Availability | |||
| Weights | Proprietary | Proprietary | Proprietary |
| API model ID | gpt-5.3-codex | qwen3.8-max | claude-sonnet-5 |
| API providers | 19 | 25 | 38 (best) |
| Released | Feb 5, 2026 | Aug 3, 2026 | Jun 30, 2026 |
| Knowledge cutoff | Aug 31, 2025 | — | Jan 31, 2026 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- GPT-5.3 Codex$45.50
- Qwen3.8 Max$32.00
- Claude Sonnet 5$40.00
Which should you choose?
Which is better: GPT-5.3 Codex, Qwen3.8 Max or Claude Sonnet 5?
Qwen3.8 Max is the better all-round choice, scoring 69/100 against Claude Sonnet 5 (66) and GPT-5.3 Codex (64). It leads on price and inputs & features. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, GPT-5.3 Codex, Qwen3.8 Max or Claude Sonnet 5?
Qwen3.8 Max is cheaper at $2.00 input / $6.00 output per million tokens (official Alibaba API price). Claude Sonnet 5 costs $2.00 input / $10.00 output per million tokens (official Anthropic API price); GPT-5.3 Codex costs $1.75 input / $14.00 output per million tokens (official OpenAI API price). At a typical mix of three input tokens to one output token, that is $3.00 per million tokens for Qwen3.8 Max versus $4.00 for Claude Sonnet 5 (1.3× as much) and $4.81 for GPT-5.3 Codex (1.6× as much).
Which scores higher on benchmarks?
GPT-5.3 Codex scores higher on the Capabilities Index (ECI): GPT-5.3 Codex 156.8 (#18 of 148), Qwen3.8 Max 156.6 (#20 of 148) and Claude Sonnet 5 156.3 (#23 of 148). The confidence ranges of the top two overlap (153.5–160.8 vs 154.5–158.8), so treat the gap as small.
Which is better for coding?
There are no published SWE-bench Verified results for Qwen3.8 Max and Claude Sonnet 5 yet, so there is no like-for-like coding score. On overall capability, GPT-5.3 Codex 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?
Qwen3.8 Max and Claude Sonnet 5 have the largest context windows (1,000,000 and 1,000,000 tokens), against 400,000 for GPT-5.3 Codex. Maximum output per response: GPT-5.3 Codex up to 128,000, Qwen3.8 Max up to 131,072, Claude Sonnet 5 up to 128,000 tokens.
Which can read images, PDFs, audio or video?
GPT-5.3 Codex accepts text, images and PDFs; Qwen3.8 Max accepts text, images, PDFs and video; Claude Sonnet 5 accepts text, images and PDFs. Qwen3.8 Max handles the widest range of inputs.
Are any of these open source?
No. GPT-5.3 Codex, Qwen3.8 Max and Claude Sonnet 5 are proprietary and only available through APIs and apps.
Which is newer?
Qwen3.8 Max is the newest, released Aug 3, 2026. Claude Sonnet 5 came out Jun 30, 2026; GPT-5.3 Codex came out Feb 5, 2026. Knowledge cutoff: GPT-5.3 Codex Aug 31, 2025, Claude Sonnet 5 Jan 31, 2026.
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.
