GPT-3.5 Turbo Instruct vs Mercury 2.5
Mercury 2.5 costs 13.3x less per output token than GPT-3.5 Turbo Instruct ($0.15 vs $2.00 per million). Updated October 23, 2026; no benchmark has tested both models yet.
- Coding
- No data
- Overall
- No data
- Output $/M
- $2.00
- Coding
- 1.6
- Overall
- No data
- Output $/M
- $0.15
GPT-3.5 Turbo Instruct or Mercury 2.5: which to pick
Only Mercury 2.5 has a coding score, 1.6 on the Vibe Coding Index; GPT-3.5 Turbo Instruct has none, so the two cannot be ranked on coding.
Compare them on price, context and the boards below.
No benchmark has tested both yet. GPT-3.5 Turbo Instruct has results on METR time horizons; Mercury 2.5 on Terminal-Bench 4 (Vals AI), Vibe Code Bench (Vals AI) and Code migration (Vals AI). Compare them on price and context instead.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Only Mercury 2.5 has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
No call
Only Mercury 2.5 has a AA Intelligence Index result, 12.3.
Directional only
Long documents
Listed context window
Mercury 2.5
Mercury 2.5 takes 260K tokens against 4K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Mercury 2.5
GPT-3.5 Turbo Instruct $0.0025, Mercury 2.5 $0.0001 per turn.
List prices
At a glance
- Coding index
- GPT-3.5 Turbo Instruct not benchmarked, Mercury 2.5 1.6 from 2 benchmarks.
- Widest category
- None yet: no category has been tested on both models.
- Widest single gap
- None yet: no benchmark has tested both models.
- Output price
- GPT-3.5 Turbo Instruct $2.00 against Mercury 2.5 $0.15 per million output tokens, 13.3x apart.
- Context window
- GPT-3.5 Turbo Instruct takes 4K tokens, Mercury 2.5 260K.
Benchmark by benchmark
Every board either model has a result on, a category to a fold; bars are each result on a 0 to 100 scale. Only one model is measured on each, so no row names a leader.
CodingDirectional onlySix of these boards feed the Vibe Coding Index9 boards measured
| Benchmark | GPT-3.5 Turbo Instruct | Mercury 2.5 | Leader |
|---|---|---|---|
| Terminal-Bench 4 (Vals AI) | Not measured | 0.0% | Only Mercury 2.5 measured |
| Vibe Code Bench (Vals AI) | Not measured | 3.7% | Only Mercury 2.5 measured |
| Code migration (Vals AI) | Not measured | 4.5% | Only Mercury 2.5 measured |
| IOI (Vals AI) | Not measured | 2.4% | Only Mercury 2.5 measured |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 34.5% | Only Mercury 2.5 measured |
| SkillsBench (Vals AI) | Not measured | 18.1% | Only Mercury 2.5 measured |
| CyberBench (Vals AI) | Not measured | 45.5% | Only Mercury 2.5 measured |
| SciCode | Not measured | 38.5% | Only Mercury 2.5 measured |
| ALE-Bench | Not measured | 301.6 | Only Mercury 2.5 measured |
| Neither model has a result on the other 34 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board measured
| Benchmark | GPT-3.5 Turbo Instruct | Mercury 2.5 | Leader |
|---|---|---|---|
| AA Intelligence Index | Not measured | 12.3 | Only Mercury 2.5 measured |
| Neither model has a result on the other 1 board here | |||
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index6 boards measured
| Benchmark | GPT-3.5 Turbo Instruct | Mercury 2.5 | Leader |
|---|---|---|---|
| Finance Agent (Vals AI) | Not measured | 18.9% | Only Mercury 2.5 measured |
| Tax Agent Bench (Vals AI) | Not measured | 2.5% | Only Mercury 2.5 measured |
| Legal Research Bench (Vals AI) | Not measured | 4.3% | Only Mercury 2.5 measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 8.8% | Only Mercury 2.5 measured |
| Terminal-Bench-Science (Vals AI) | Not measured | 0.0% | Only Mercury 2.5 measured |
| METR time horizons | 21.5% | Not measured | Only GPT-3.5 Turbo Instruct measured |
| Neither model has a result on the other 36 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index1 board measured
| Benchmark | GPT-3.5 Turbo Instruct | Mercury 2.5 | Leader |
|---|---|---|---|
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 11.8% | Only Mercury 2.5 measured |
| Neither model has a result on the other 22 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index1 board measured
| Benchmark | GPT-3.5 Turbo Instruct | Mercury 2.5 | Leader |
|---|---|---|---|
| ProofBench | Not measured | 3.0% | Only Mercury 2.5 measured |
| Neither model has a result on the other 13 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index2 boards measured
| Benchmark | GPT-3.5 Turbo Instruct | Mercury 2.5 | Leader |
|---|---|---|---|
| LegalBench (Vals AI) | Not measured | 83.1% | Only Mercury 2.5 measured |
| MedCode (Vals AI) | Not measured | 31.3% | Only Mercury 2.5 measured |
| Neither model has a result on the other 18 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index3 boards measured
| Benchmark | GPT-3.5 Turbo Instruct | Mercury 2.5 | Leader |
|---|---|---|---|
| Public Benefits Bench (Vals AI) | Not measured | 45.3% | Only Mercury 2.5 measured |
| MedScribe (Vals AI) | Not measured | 55.1% | Only Mercury 2.5 measured |
| Long context reasoning (AA-LCR) | Not measured | 71.7% | Only Mercury 2.5 measured |
| Neither model has a result on the other 45 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
Mercury 2.5 costs less
Repository review
50K input + 3K output tokens
Mercury 2.5 costs less
Agent loop
200K input + 10K output tokens
Mercury 2.5 costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | OpenAI GPT-3.5 Turbo Instruct | Inception Mercury 2.5 |
|---|---|---|
| Maker | OpenAI | Inception |
| Weights | No public weights listed | No public weights listed |
| Released | September 28, 2023 | September 8, 2026 |
| Context window | 4K | 260K |
| Input $/Mtok | $1.50 | $0.04 |
| Output $/Mtok | $2.00 | $0.15 |
| Coding index | Not benchmarked | 1.6 |
| Independent measurements behind it | 0 | 2 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-3.5 Turbo Instruct better than Mercury 2.5 for coding?
Only Mercury 2.5 has a coding score, 1.6 on the Vibe Coding Index; GPT-3.5 Turbo Instruct has none, so the two cannot be ranked on coding. Compare them on price, context and the boards below.
Which is cheaper, GPT-3.5 Turbo Instruct or Mercury 2.5?
GPT-3.5 Turbo Instruct costs $1.50 per million input tokens and $2.00 per million output tokens; Mercury 2.5 costs $0.04 and $0.15. Cost per solved task is known for neither of them.
Which has the bigger context window, GPT-3.5 Turbo Instruct or Mercury 2.5?
Mercury 2.5, with 260K tokens against 4K.
Has any benchmark tested both GPT-3.5 Turbo Instruct and Mercury 2.5?
No benchmark has tested both yet. GPT-3.5 Turbo Instruct has results on METR time horizons; Mercury 2.5 on Terminal-Bench 4 (Vals AI), Vibe Code Bench (Vals AI) and Code migration (Vals AI). Compare them on price and context instead. Data as of October 23, 2026.