GLM 5.3 Flash on finance benchmarks
It scores within about eight points of the Finance Agent v2 leader for $0.05 per test, the lowest cost among the top 15.
What it is
GLM 5.3 Flash is an open-weight model from Z.ai, released August 26, 2026, with a 1M-token context window. Vals AI ran it through Fireworks AI at max reasoning effort. Developer documentation listed by Vals: docs.z.ai.
| Developer | Z.ai (zAI) |
|---|---|
| Release date | Aug 26, 2026 |
| Context window | 1M tokens |
| Weights | Open |
| Public API price | $0.07 input / $0.25 output per million tokens, listed (source) |
What published results say
| Benchmark | Score | Rank | Context |
|---|---|---|---|
| Finance Agent v2 | 57.85% | #13 of 78 | Context: n=450 test questions, 3 runs · Oct 12, 2026 leaderboard · Vals AI · ±2.06 SEM |
| Excel Modeling Benchmark | 55.93% | #47 of 74 | Context: n=51 test tasks · Oct 12, 2026 leaderboard · Vals AI · ±3.56 as published, type not stated |
| Tax Agent Bench | 31.55% | #21 of 69 | Context: n=193 test questions · Oct 12, 2026 leaderboard · Vals AI · ±3.35 as published, type not stated |
- Finance Agent v2 cost and time per task: $0.05, 14m51s.
What the benchmarks test: FAB v2, filing-based analyst research questions; EMB, building Excel financial models (LBO, DCF, M&A, comps); Tax Agent, research-grade US corporate tax questions, all-or-nothing grading. All three use held-out test sets and AI judges.
Limits
- Its Finance Agent v2 margin (plus or minus 2.06) is the widest in this directory, so its rank is less settled than the leaders'.
- Vals lists two slightly different input prices: $0.07 on the model page and $0.075 in the Finance Agent v2 table.
- Weak on Excel modeling (47th of 74).
- Benchmarks measure research and modeling answers, not trading results.
Head-to-head
Primary sources
- VerifiedGLM 5.3 Flash model page (Vals AI)Scores, margins, release date, context window and token prices checked October 14, 2026.
- VerifiedFinance Agent v2 leaderboard and methodology (Vals AI)Sample size, grading and update date checked October 14, 2026.
- VerifiedExcel Modeling Benchmark leaderboard and methodology (Vals AI)Sample size, grading and update date checked October 14, 2026.
- VerifiedTax Agent Bench leaderboard and methodology (Vals AI)Sample size, grading and update date checked October 14, 2026.
- LinkedDeveloper documentation (Z.ai (zAI))Linked by Vals AI. Not re-checked by us.
Related stories
- AI Analyst ScoreboardThe best AI analyst scores 65.4% on a Wall Street research test
Last verified: . Prices and scores change; check the primary source before relying on them. We have no affiliate links and receive nothing from the companies listed. Every percentage carries its sample size, period and source (no naked percentages).
Not financial advice. For information and education only. Benchmark scores and vendor descriptions are not trading results and do not predict returns. Nothing here is a recommendation to buy or sell any asset or to subscribe to any product. See our disclaimer.