Apodex 1.1
ApodexProprietaryReasoningProvisionalReleased Aug 24, 2026
Overall score
50.3
Rank 96 of 222 · 35.9–64.6
Context window
—
Price per 1M tokens
— in · — out
No price listed
Blended price
—
3:1 input:output tokens
Output speed
—
Not measured yet
Category scores
Scores per capability area with the model's rank among ranked models in that category.
- 1Multimodal81.1
- 2Knowledge79.8
- 3Reasoning79.5
- 4Coding66.1
Benchmark results (9)
As reported in system cards, papers and public evaluations. Position compares this model with every other model reporting the same benchmark.
Agentic & tool use
| Terminal-Bench 2.1 | 70.8 | #40 of 68 |
| HLE w/ tools | 56.1 | #12 of 27 |
| DeepSearchQA | 92.4 | #7 of 20 |
| APEX-Agents | 38.5 | #2 of 8 |
Knowledge
| HLE | 56.1 | #9 of 69 |
| BioMysteryBench (human-difficult) | 35.3 | #6 of 6 |
| FrontierScience Research | 63.3 | #1 of 2 |
Coding
| SWE-bench Verified | 77.7 | #28 of 98 |
Math
| IMO 2026 | 31 | #2 of 2 |
Pricing by source
USD per 1M tokens.
| Source | Input | Output | Cached in |
|---|---|---|---|
| List price | — | — | — |
Apodex's web workbench uses dynamic credit billing based on model tokens and tool calls, while the release post says bare-model API access will roll out later. Apodex does not publish a comparable first-party input/output token rate or context limit for the full 397B model.
Speed
Measured by us through OpenRouter (median of trials).
Not available on OpenRouter, so we cannot measure it yet.
Related models
Similar score
- DeepSeek V3.250.2 · $0.32
- GPT-5.1-Codex50.4 · $3.44
- MiMo-V2-Omni50.0 · —
- MiniMax M2.550.0 · $0.53
- GLM-5V-Turbo49.6 · $1.90