#41 GPT-5.3 Chat
none- Cost
- $0.008
- Time
- 8.1s
- Tokens
- 634 tok
OpenAI
Release: 2026-03-03
Tested on: 2026-04-11 01:44
openai/gpt-5.3-chat::none
~400B total (~17B active)MoEClosedEstimated Summary
GPT 5.3 Chat scores 7.7 on AI BENCHY and ranks #41. It has N/A reliability, a 68.5% pass rate, $0.340 total cost, and 5.88s average response time.
What makes GPT 5.3 Chat unique: It stands out most in Puzzle Solving, where it ranks #1, while Anti-AI Tricks is its weakest area at #17. Its total benchmark cost is unusually low for its score range. It is notably fast compared with similar models.
Model facts
Researched on 2026-08-12
- Parameters
- ~400B total (~17B active)
- Architecture
- MoE
- Availability
- Closed
- License
- -
Best estimate from public evidence; the vendor did not disclose every value. Vendor does not disclose the architecture or count.
7.7
Consistency
8.6
N/A
$0.340
Total Output Tokens
20,784
Total Input Tokens
0
Input Price
$1.750 / 1M
Output Price
$14.000 / 1M
Flaky tests
3
Flaky tests had mixed outcomes across runs (at least one pass and one fail).
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
Run history
| Tested on | Score | Reliability | Tests Correct | Total Cost | Compare |
|---|---|---|---|---|---|
| 2026-08-14 02:24 Re-test | 7.5 | 10.0 | $0.533 | Compare | |
| 2026-07-16 22:40 New test added | 7.5 | 10.0 | $0.571 | Compare | |
| 2026-06-04 13:47 New test added | 7.2 | 10.0 | $0.433 | Compare | |
| 2026-05-22 00:20 Re-test | 7.4 | 10.0 | $0.401 | Compare | |
| 2026-04-11 01:44 First recorded run | 7.7 | N/A | $0.340 | Current run |
Run comparison
| Run | Benchmark coverage | Score | Consistency | Reliability | Tests Correct | Flaky tests | Total Output Tokens | Total Input Tokens | Total Cost | Response Time (avg) |
|---|---|---|---|---|---|---|---|---|---|---|
| 2026-04-11 01:44 · First recorded run | 54/54 attempts | 7.7 | 8.6 | N/A | 11/18 | 3 | 20,784 | 0 | $0.340 | 5.88s |
| 2026-08-14 02:24 · Re-test | 66/66 attempts | 7.5 | 8.6 | 10.0 | 13/22 | 4 | 28,179 | 78,846 | $0.533 | 6.56s |
| Difference | — | +0.2 | 0.0 | -2 | -1 | -7395 | -78846 | -$0.194 | -678ms |
Benchmark coverage differs: 54/54 attempts (Target: 3 repeats per test) versus 66/66 attempts (Target: 3 repeats per test). Totals and repeat-sensitive metrics are not directly comparable.
These two runs used different benchmark suites, so the deltas reflect both model changes and suite changes.
Charts
Choose the first model, then click a second model to open a side-by-side page.
Top Models by Score
Score vs Total Cost
Response Time (avg)
Score vs Response Time (avg)
Total Output Tokens
Score vs Total Output Tokens
Quick Compare
GPT 5.3 ChatnonevsMiniMax M3mediumGPT 5.3 ChatnonevsQwen3.5 Plus 2026-02-15mediumGPT 5.3 ChatnonevsGPT-5.6 TerralowGPT 5.3 ChatnonevsQwen3.5-27BmediumGPT 5.3 ChatnonevsGPT-5.4 NanomediumGPT 5.3 ChatnonevsGPT-5.4 MinimediumGPT 5.3 ChatnonevsClaude Opus 5noneGPT 5.3 ChatnonevsGrok Build 0.1mediumGPT 5.3 ChatnonevsNemotron 3 UltramediumFree AvailableGPT 5.3 ChatnonevsGemini 3.1 Flash Lite Previewmedium
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Anti-AI Tricks | 6.7 | 8.1 | |
| Coding | 10.0 | 10.0 | |
| Combined | 10.0 | 10.0 | |
| Data parsing and extraction | 10.0 | 10.0 | |
| Domain specific | 3.5 | 4.4 | |
| General Intelligence | 4.6 | 10.0 | |
| Instructions following | 8.3 | 10.0 | |
| Puzzle Solving | 10.0 | 10.0 | |
| Tool Calling | 10.0 | 10.0 |