CorpFin v2 leaderboard (Aug 2026): AI model scores
As of 12 Aug 2026, the highest reported Alibaba score on CorpFin v2 is Qwen 3 Max Thinking (Alibaba) at 68.03%, #12 on that leaderboard, per Vals AI. The source no longer updates this leaderboard.
What it measures
Understanding long-context credit agreements (private benchmark).
Questions about long credit agreements, testing understanding of long financial documents.
What the score means
Accuracy
Share of questions answered correctly.
Results from published AI leaderboards. Compare models within each benchmark; scores from different tests aren’t directly comparable. How we collect these results
Scores by model
Run by Vals AI. Leaderboard dated 12 Aug 2026 (no longer updated by the source). Last checked 22 Oct 2026. Showing top 25 of 134 models listed.
Highlight a provider: Anthropic OpenAI Google xAI Meta Alibaba Z.ai Moonshot MiniMax
Highlighting Alibaba models. Other providers are dimmed. Show all providers
- Anthropic
- OpenAI
- xAI
- Meta
- Alibaba
- Z.ai
- Moonshot
- MiniMax
- Other
- Accuracy
- Share of questions answered correctly.
All scores
| Rank | Model | Provider | Accuracy | Price in / out ($/1M tokens) |
|---|---|---|---|---|
| 1 | Claude Opus 5 | Anthropic | 73.19% | $5 / $25 |
| 2 | Claude Fable 5 | Anthropic | 71.83% | $10 / $50 |
| 3 | Kimi K3 | Moonshot | 71.56% | $3 / $15 |
| 4 | Muse Spark 1.1 | Meta | 71.29% | $1.25 / $4.25 |
| 5 | Muse Spark 1.2 | Meta | 70.94% | $1.25 / $4.25 |
| 6 | Inkling Small | Other | 69.62% | $0.3 / $1.2 |
| 7 | Inkling | Other | 68.57% | $1 / $4.05 |
| 8 | Grok 4.3 | xAI | 68.53% | $1.25 / $2.5 |
| 9 | GPT 5.5 | OpenAI | 68.42% | $5 / $30 |
| 10 | Kimi K2.5 | Moonshot | 68.26% | $0.6 / $3 |
Show 15 more rows
| Rank | Model | Provider | Accuracy | Price in / out ($/1M tokens) |
|---|---|---|---|---|
| 11 | MiniMax-M3 | MiniMax | 68.10% | $0.6 / $2.4 |
| 12 | Qwen 3 Max Thinking | Alibaba | 68.03% | $1.2 / $6 |
| 13 | Grok 4.5 | xAI | 67.41% | $2 / $6 |
| 14 | Claude Opus 4.6 (Thinking) | Anthropic | 67.02% | $5 / $25 |
| 15 | Claude Sonnet 5 | Anthropic | 66.98% | $2 / $10 |
| 16 | Grok 4 Fast (Reasoning) | xAI | 66.90% | $0.2 / $0.5 |
| 17 | Kimi K2.6 | Moonshot | 66.74% | $0.95 / $4 |
| 18 | Claude Opus 4.8 | Anthropic | 66.71% | $5 / $25 |
| 19 | Qwen 3.6 Max Preview | Alibaba | 66.47% | $1.3 / $7.8 |
| 20 | Gemini 3 Flash (12/25) | 66.43% | $0.5 / $3 | |
| 21 | Grok 4.6 | xAI | 66.16% | $2 / $6 |
| 22 | GLM 5.2 | Z.ai | 66.12% | $1.4 / $4.4 |
| 23 | Claude Opus 4.7 | Anthropic | 66.08% | $5 / $25 |
| 24 | Grok 4 | xAI | 66.05% | $3 / $15 |
| 25 | Grok 4.1 Fast (Reasoning) | xAI | 65.97% | $0.2 / $0.5 |
Source: Vals AI leaderboard ↗
Best-ranked Alibaba model here: Qwen 3 Max Thinking (Alibaba). Browse prompts for any model →
Prompts for this kind of work
Copy-ready prompts from our library that match what CorpFin v2 tests. Run them on your own material to compare models.