Leaderboard
Toolathlon
8 models scored · metric: success rate. Prices are the cheapest listed across all serving providers. Pts/$ = score ÷ blended price (3×input + output) / 4 — how much score each dollar buys.
Best value · top 5 by pts per dollar
- 1.GPT-5.6 Luna237
- 2.Step 3.7 Flash119
- 3.GPT-5.4 nano86.6
- 4.GPT-5.4 mini28.4
- 5.GPT-5.6 Terra23.6
| # | Model | Score | Best in /M | Best out /M | Pts / $ | Context |
|---|---|---|---|---|---|---|
| 🥇 | GPT-5.6 Solopenai | 58 | $2.50 | $15 | 10.3 | 1.05M |
| 🥈 | Gemini 3.5 Flashgoogle | 56.5 | $1.50 | $9 | 16.7 | 1.05M |
| 🥉 | GPT-5.5openai | 55.6 | $4.55 | $27.27 | 5.4 | 1.05M |
| 4 | GPT-5.6 Lunaopenai | 53.4 | $0.1 | $0.6 | 237 | 1.05M |
| 5 | GPT-5.6 Terraopenai | 53.1 | $1 | $6 | 23.6 | 1.05M |
| 6 | Step 3.7 Flashstepfun | 49.5 | $0.185 | $1.11 | 119 | 256K |
| 7 | GPT-5.4 miniopenai | 42.9 | $0.68 | $4 | 28.4 | 400K |
| 8 | GPT-5.4 nanoopenai | 35.5 | $0.18 | $1.10 | 86.6 | 400K |
Cheapest scorer: GPT-5.6 Luna at $0.1 input /M.