> ## Documentation Index
> Fetch the complete documentation index at: https://docs.magnitude.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Benchmark

> Terminal-Bench 2.1 results

Terminal-Bench 2.1 is the latest version of the standard agentic coding benchmark: 89 tasks, 5 trials each, 445 total runs. We ran Magnitude alongside Claude Code and OpenCode, all using the same model (GLM-5.2), and compared against Anthropic's official Claude Code + Opus 4.8 run from the tbench.ai leaderboard.

## Results

| Agent         | Model    | Success Rate        | Cost / success |
| ------------- | -------- | ------------------- | -------------- |
| Claude Code   | Opus 4.8 | **78.9%** (351/445) | \~\$1.20       |
| **Magnitude** | GLM-5.2  | **75.5%** (336/445) | **\$0.42**     |
| Claude Code   | GLM-5.2  | 70.8% (315/445)     | \$0.60         |
| OpenCode      | GLM-5.2  | 50.8% (226/445)     | \$0.59         |

Magnitude is the highest-performing GLM-5.2 agent, beating Claude Code on the same model by 4.7 points, with the best cost per successful trial (\$0.42). Against Claude Code on Opus 4.8, Magnitude trails by 3.4 points but at roughly one-third the cost per success.

## Cost efficiency

| Cost component | Magnitude    | Claude Code  | OpenCode     |
| -------------- | ------------ | ------------ | ------------ |
| Uncached input | \$23.11      | \$92.74      | \$38.11      |
| Cached input   | \$79.69      | \$54.68      | \$68.96      |
| Output         | \$39.04      | \$43.09      | \$27.10      |
| **Total**      | **\$141.84** | **\$190.51** | **\$134.17** |

The Opus 4.8 run costs \~\$420.67 (corrected from tbench.ai; see methodology), nearly 3x Magnitude's cost for a 3.4 point improvement.

## Methodology

* **Benchmark:** Terminal-Bench 2.1, 89 tasks, 5 trials each, 445 total
* **Infrastructure:** All GLM-5.2 runs on identical task set via Fireworks serverless endpoint
* **Success classification:** `verifier_result.rewards.reward > 0` = pass
* **GLM-5.2 cost:** `(uncached_input × \$1.40 + cached_input × \$0.14 + output × \$4.40) / 1M`
* **Opus 4.8 cost:** Corrected from tbench.ai leaderboard, which charged cached input at \$0/M instead of the real \$0.50/M cache-read rate. Corrected total adds \~\$132.58 in cache-read costs. This is a floor; 6 trials are missing from tbench.ai data.